{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/mim","slug":"mim","name":"MIM","full_name":"Mutual Information Machine/Mask Image Modeling","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"MIM: Mutual Information Machine","paper":"/paper/mim-mutual-information-machine","first_author":"Micha Livne","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mim-mutual-information-machine"},"source":{"url":"https://arxiv.org/abs/1910.03175v5","title":"MIM: Mutual Information Machine","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Representation Learning","url":"/methods/category/representation-learning","pwc_aliases":[]}],"n_papers_tagged":150,"archive_num_papers":150,"papers_newest_first":[{"paper":"/paper/boosting-generative-adversarial","slug":"boosting-generative-adversarial","title":"Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features","date":"2025-06-26","arxiv_id":"2506.21046","n_code_links":1,"syntology":null},{"paper":"/paper/attention-please-revisiting-attentive-probing","slug":"attention-please-revisiting-attentive-probing","title":"Attention, Please! Revisiting Attentive Probing for Masked Image Modeling","date":"2025-06-11","arxiv_id":"2506.10178","n_code_links":1,"syntology":null},{"paper":null,"slug":"joint-low-level-and-high-level-textual","title":"Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies","date":"2025-05-11","arxiv_id":"2505.06855","n_code_links":0,"syntology":null},{"paper":null,"slug":"dependency-structure-augmented-contextual","title":"Dependency Structure Augmented Contextual Scoping Framework for Multimodal Aspect-Based Sentiment Analysis","date":"2025-04-15","arxiv_id":"2504.11331","n_code_links":0,"syntology":null},{"paper":null,"slug":"resilience-of-vision-transformers-for-domain","title":"Resilience of Vision Transformers for Domain Generalisation in the Presence of Out-of-Distribution Noisy Images","date":"2025-04-05","arxiv_id":"2504.04225","n_code_links":0,"syntology":null},{"paper":null,"slug":"mimrs-a-survey-on-masked-image-modeling-in","title":"MIMRS: A Survey on Masked Image Modeling in Remote Sensing","date":"2025-04-04","arxiv_id":"2504.03181","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfmedhpm-self-pre-training-with-hard","title":"SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation","date":"2025-04-03","arxiv_id":"2504.02524","n_code_links":0,"syntology":null},{"paper":"/paper/linguistics-aware-masked-image-modeling-for","slug":"linguistics-aware-masked-image-modeling-for","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","date":"2025-03-24","arxiv_id":"2503.18746","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":6,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhangyifei01/LMIM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"conjuring-positive-pairs-for-efficient","title":"Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis","date":"2025-03-19","arxiv_id":"2503.15060","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-modal-federated-learning-framework","title":"A Multi-Modal Federated Learning Framework for Remote Sensing Image Classification","date":"2025-03-13","arxiv_id":"2503.10262","n_code_links":0,"syntology":null},{"paper":null,"slug":"miram-masked-image-reconstruction-across","title":"MIRAM: Masked Image Reconstruction Across Multiple Scales for Breast Lesion Risk Prediction","date":"2025-03-10","arxiv_id":"2503.07157","n_code_links":0,"syntology":null},{"paper":null,"slug":"wavelet-driven-masked-image-modeling-a-path","title":"Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation","date":"2025-03-02","arxiv_id":"2503.00782","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmim-a-contrastive-mutual-information","title":"cMIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning","date":"2025-02-27","arxiv_id":"2502.19642","n_code_links":0,"syntology":null},{"paper":"/paper/escaping-the-big-data-paradigm-in-self","slug":"escaping-the-big-data-paradigm-in-self","title":"Escaping The Big Data Paradigm in Self-Supervised Representation Learning","date":"2025-02-25","arxiv_id":"2502.18056","n_code_links":1,"syntology":null},{"paper":"/paper/cluster-and-predict-latents-patches-for","slug":"cluster-and-predict-latents-patches-for","title":"Cluster and Predict Latents Patches for Improved Masked Image Modeling","date":"2025-02-12","arxiv_id":"2502.08769","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/capi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/hi-end-mae-hierarchical-encoder-driven-masked","slug":"hi-end-mae-hierarchical-encoder-driven-masked","title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation","date":"2025-02-12","arxiv_id":"2502.08347","n_code_links":1,"syntology":null},{"paper":null,"slug":"mim-multi-modal-content-interest-modeling","title":"MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling","date":"2025-02-01","arxiv_id":"2502.00321","n_code_links":0,"syntology":null},{"paper":"/paper/pilamim-toward-richer-visual-representations","slug":"pilamim-toward-richer-visual-representations","title":"PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling","date":"2025-01-06","arxiv_id":"2501.03005","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-cls-exploring-the-true-potential-of","slug":"beyond-cls-exploring-the-true-potential-of","title":"Beyond [cls]: Exploring the true potential of Masked Image Modeling representations","date":"2024-12-04","arxiv_id":"2412.03215","n_code_links":1,"syntology":null},{"paper":"/paper/satvision-toa-a-geospatial-foundation-model","slug":"satvision-toa-a-geospatial-foundation-model","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","date":"2024-11-26","arxiv_id":"2411.17000","n_code_links":1,"syntology":null},{"paper":"/paper/relational-contrastive-learning-and-masked","slug":"relational-contrastive-learning-and-masked","title":"Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition","date":"2024-11-18","arxiv_id":"2411.11219","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-prototypes-to-general-distributions-an","title":"From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling","date":"2024-11-16","arxiv_id":"2411.10685","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-real-zero-shot-camouflaged-object","title":"Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations","date":"2024-10-22","arxiv_id":"2410.16953","n_code_links":0,"syntology":null},{"paper":"/paper/domain-adaptive-pre-training-of-self","slug":"domain-adaptive-pre-training-of-self","title":"Domain-Adaptive Pre-training of Self-Supervised Foundation Models for Medical Image Classification in Gastrointestinal Endoscopy","date":"2024-10-21","arxiv_id":"2410.21302","n_code_links":1,"syntology":null},{"paper":"/paper/ladmim-logical-anomaly-detection-with-masked","slug":"ladmim-logical-anomaly-detection-with-masked","title":"LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space","date":"2024-10-14","arxiv_id":"2410.10234","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-learning-for-real-world","title":"Self-Supervised Learning for Real-World Object Detection: a Survey","date":"2024-10-09","arxiv_id":"2410.07442","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-pretraining-for-1","slug":"self-supervised-pretraining-for-1","title":"Self-supervised Pretraining for Cardiovascular Magnetic Resonance Cine Segmentation","date":"2024-09-26","arxiv_id":"2409.18100","n_code_links":1,"syntology":null},{"paper":null,"slug":"interactive-masked-image-modeling-for","title":"Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing","date":"2024-09-13","arxiv_id":"2409.08885","n_code_links":0,"syntology":null},{"paper":null,"slug":"explicit-mutual-information-maximization-for","title":"Explicit Mutual Information Maximization for Self-Supervised Learning","date":"2024-09-07","arxiv_id":"2409.04747","n_code_links":0,"syntology":null},{"paper":null,"slug":"sg-mim-structured-knowledge-guided-efficient","title":"SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction","date":"2024-09-04","arxiv_id":"2409.02513","n_code_links":0,"syntology":null},{"paper":"/paper/micm-rethinking-unsupervised-pretraining-for","slug":"micm-rethinking-unsupervised-pretraining-for","title":"MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning","date":"2024-08-23","arxiv_id":"2408.13385","n_code_links":1,"syntology":null},{"paper":null,"slug":"symmetric-masking-strategy-enhances-the","title":"Symmetric masking strategy enhances the performance of Masked Image Modeling","date":"2024-08-23","arxiv_id":"2408.12772","n_code_links":0,"syntology":null},{"paper":"/paper/masked-image-modeling-a-survey","slug":"masked-image-modeling-a-survey","title":"Masked Image Modeling: A Survey","date":"2024-08-13","arxiv_id":"2408.06687","n_code_links":1,"syntology":null},{"paper":null,"slug":"membership-inference-attack-against-masked","title":"Membership Inference Attack Against Masked Image Modeling","date":"2024-08-13","arxiv_id":"2408.06825","n_code_links":0,"syntology":null},{"paper":"/paper/qpt-v2-masked-image-modeling-advances-visual","slug":"qpt-v2-masked-image-modeling-advances-visual","title":"QPT V2: Masked Image Modeling Advances Visual Scoring","date":"2024-07-23","arxiv_id":"2407.16541","n_code_links":1,"syntology":null},{"paper":"/paper/towards-latent-masked-image-modeling-for-self","slug":"towards-latent-masked-image-modeling-for-self","title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning","date":"2024-07-22","arxiv_id":"2407.15837","n_code_links":1,"syntology":{"ran":21,"of":29,"n_ran_checked":18,"n_instrument":3,"unverified":8,"pointer_only":29,"phrase":"21 ran (of which 10 constructed an object rather than computing a result; 18 with no instrument failure: 5 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["yibingwei-1/latentmim"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":10,"n_ran_no_instrument_failure":18,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"x-former-unifying-contrastive-and","title":"X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs","date":"2024-07-18","arxiv_id":"2407.13851","n_code_links":0,"syntology":null},{"paper":null,"slug":"aemim-adversarial-examples-meet-masked-image","title":"AEMIM: Adversarial Examples Meet Masked Image Modeling","date":"2024-07-16","arxiv_id":"2407.11537","n_code_links":0,"syntology":null},{"paper":"/paper/enhanced-self-supervised-learning-for-multi","slug":"enhanced-self-supervised-learning-for-multi","title":"Enhanced Masked Image Modeling to Avoid Model Collapse on Multi-modal MRI Datasets","date":"2024-07-15","arxiv_id":"2407.10377","n_code_links":2,"syntology":null},{"paper":"/paper/on-the-role-of-discrete-tokenization-in","slug":"on-the-role-of-discrete-tokenization-in","title":"On the Role of Discrete Tokenization in Visual Representation Learning","date":"2024-07-12","arxiv_id":"2407.09087","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["pku-ml/clustermim"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tissue-contrastive-semi-masked-autoencoders","title":"Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT","date":"2024-07-12","arxiv_id":"2407.08961","n_code_links":0,"syntology":null},{"paper":"/paper/anatomask-enhancing-medical-image","slug":"anatomask-enhancing-medical-image","title":"AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking","date":"2024-07-09","arxiv_id":"2407.06468","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ricklisz/anatomask"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-efficient-masked-autoencoder-learning","slug":"scaling-efficient-masked-autoencoder-learning","title":"Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset","date":"2024-06-17","arxiv_id":"2406.11933","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":1,"n_instrument":3,"unverified":3,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Fengxiang23/SelectiveMAE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/semanticmim-marring-masked-image-modeling","slug":"semanticmim-marring-masked-image-modeling","title":"SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation","date":"2024-06-15","arxiv_id":"2406.10673","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-vision-language-model-with-unmasked","slug":"enhancing-vision-language-model-with-unmasked","title":"Enhancing Vision-Language Model with Unmasked Token Alignment","date":"2024-05-29","arxiv_id":"2405.19009","n_code_links":1,"syntology":null},{"paper":"/paper/mamba-in-mamba-centralized-mamba-cross-scan","slug":"mamba-in-mamba-centralized-mamba-cross-scan","title":"Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification","date":"2024-05-20","arxiv_id":"2405.12003","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-pretraining-model-based-on-multi","title":"Efficient Pretraining Model based on Multi-Scale Local Visual Field Feature Reconstruction for PCB CT Image Element Segmentation","date":"2024-05-09","arxiv_id":"2405.05745","n_code_links":0,"syntology":null},{"paper":null,"slug":"mim-mask-in-mask-self-supervised-pre-training","title":"MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis","date":"2024-04-24","arxiv_id":"2404.15580","n_code_links":0,"syntology":null},{"paper":"/paper/observation-analysis-and-solution-exploring","slug":"observation-analysis-and-solution-exploring","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","date":"2024-04-18","arxiv_id":"2404.12210","n_code_links":1,"syntology":null},{"paper":null,"slug":"emerging-property-of-masked-token-for","title":"Emerging Property of Masked Token for Effective Pre-training","date":"2024-04-12","arxiv_id":"2404.08330","n_code_links":0,"syntology":null},{"paper":"/paper/masked-image-modeling-as-a-framework-for-self","slug":"masked-image-modeling-as-a-framework-for-self","title":"Masked Image Modeling as a Framework for Self-Supervised Learning across Eye Movements","date":"2024-04-12","arxiv_id":"2404.08526","n_code_links":1,"syntology":null},{"paper":"/paper/dailymae-towards-pretraining-masked","slug":"dailymae-towards-pretraining-masked","title":"DailyMAE: Towards Pretraining Masked Autoencoders in One Day","date":"2024-03-31","arxiv_id":"2404.00509","n_code_links":1,"syntology":null},{"paper":"/paper/content-aware-masked-image-modeling","slug":"content-aware-masked-image-modeling","title":"CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression","date":"2024-03-13","arxiv_id":"2403.08505","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-provably-learn-feature-position","title":"A Theoretical Analysis of Self-Supervised Learning for Vision Transformers","date":"2024-03-04","arxiv_id":"2403.02233","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantics-enhanced-cross-modal-masked-image","title":"Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training","date":"2024-03-01","arxiv_id":"2403.00249","n_code_links":0,"syntology":null},{"paper":"/paper/mim-reasoner-learning-with-theoretical","slug":"mim-reasoner-learning-with-theoretical","title":"MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization","date":"2024-02-24","arxiv_id":"2402.16898","n_code_links":1,"syntology":null},{"paper":"/paper/mim-refiner-a-contrastive-learning-boost-from","slug":"mim-refiner-a-contrastive-learning-boost-from","title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","date":"2024-02-15","arxiv_id":"2402.10093","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-jku/MIM-Refiner"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/amused-an-open-muse-reproduction","slug":"amused-an-open-muse-reproduction","title":"aMUSEd: An Open MUSE Reproduction","date":"2024-01-03","arxiv_id":"2401.01808","n_code_links":1,"syntology":null},{"paper":"/paper/masked-image-modeling-via-dynamic-token","slug":"masked-image-modeling-via-dynamic-token","title":"Morphing Tokens Draw Strong Masked Image Models","date":"2023-12-30","arxiv_id":"2401.00254","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["naver-ai/dtm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/towards-reliable-ai-model-deployments","slug":"towards-reliable-ai-model-deployments","title":"Towards Reliable AI Model Deployments: Multiple Input Mixup for Out-of-Distribution Detection","date":"2023-12-24","arxiv_id":"2312.15514","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-universal-medical-image","slug":"pre-trained-universal-medical-image","title":"Building Universal Foundation Models for Medical Image Analysis with Spatially Adaptive Networks","date":"2023-12-12","arxiv_id":"2312.07630","n_code_links":1,"syntology":null},{"paper":null,"slug":"intelligent-anomaly-detection-for-lane","title":"Intelligent Anomaly Detection for Lane Rendering Using Transformer with Self-Supervised Pre-Training and Customized Fine-Tuning","date":"2023-12-07","arxiv_id":"2312.04398","n_code_links":0,"syntology":null},{"paper":null,"slug":"improve-supervised-representation-learning","title":"Improve Supervised Representation Learning with Masked Image Modeling","date":"2023-12-01","arxiv_id":"2312.00950","n_code_links":0,"syntology":null},{"paper":null,"slug":"bim-block-wise-self-supervised-learning-with","title":"BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling","date":"2023-11-28","arxiv_id":"2311.17218","n_code_links":0,"syntology":null},{"paper":"/paper/time-optimal-control-for-high-order-chain-of","slug":"time-optimal-control-for-high-order-chain-of","title":"Time-Optimal Control for High-Order Chain-of-Integrators Systems with Full State Constraints and Arbitrary Terminal States (Extended Version)","date":"2023-11-13","arxiv_id":"2311.07039","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-cross-domain-sequential","slug":"rethinking-cross-domain-sequential","title":"Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions","date":"2023-11-08","arxiv_id":"2311.04590","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["wujiangxu/amid"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-supervised-learning-for-visual","slug":"self-supervised-learning-for-visual","title":"Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction","date":"2023-11-08","arxiv_id":"2311.04834","n_code_links":1,"syntology":null},{"paper":"/paper/hap-structure-aware-masked-image-modeling-for-1","slug":"hap-structure-aware-masked-image-modeling-for-1","title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","date":"2023-10-31","arxiv_id":"2310.20695","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["junkunyuan/hap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pre-training-with-random-orthogonal","slug":"pre-training-with-random-orthogonal","title":"Pre-training with Random Orthogonal Projection Image Modeling","date":"2023-10-28","arxiv_id":"2310.18737","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csiro-robotics/ropim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/longer-range-contextualized-masked","slug":"longer-range-contextualized-masked","title":"Learning with Unmasked Tokens Drives Stronger Vision Learners","date":"2023-10-20","arxiv_id":"2310.13593","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver-ai/lut"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adversarial-masked-image-inpainting-for","title":"Adversarial Masked Image Inpainting for Robust Detection of Mpox and Non-Mpox","date":"2023-10-10","arxiv_id":"2310.06318","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-neuron-segmentation-with","slug":"self-supervised-neuron-segmentation-with","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","date":"2023-10-06","arxiv_id":"2310.04148","n_code_links":1,"syntology":{"ran":20,"of":24,"n_ran_checked":18,"n_instrument":2,"unverified":4,"pointer_only":24,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ydchen0806/dbmim"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":4,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-distilled-masked-attention-guided-masked","title":"Self-distilled Masked Attention guided masked image modeling with noise Regularized Teacher (SMART) for medical image analysis","date":"2023-10-02","arxiv_id":"2310.01209","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-generative-knowledge","title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling","date":"2023-09-18","arxiv_id":"2309.09571","n_code_links":0,"syntology":null},{"paper":"/paper/textbind-multi-turn-interleaved-multimodal","slug":"textbind-multi-turn-interleaved-multimodal","title":"TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild","date":"2023-09-14","arxiv_id":"2309.08637","n_code_links":1,"syntology":null},{"paper":null,"slug":"bilma-bidirectional-local-matching-for-text","title":"BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification","date":"2023-09-09","arxiv_id":"2309.04675","n_code_links":0,"syntology":null},{"paper":"/paper/revcolv2-exploring-disentangled-1","slug":"revcolv2-exploring-disentangled-1","title":"RevColV2: Exploring Disentangled Representations in Masked Image Modeling","date":"2023-09-02","arxiv_id":"2309.01005","n_code_links":1,"syntology":null},{"paper":"/paper/improving-pixel-based-mim-by-reducing-wasted","slug":"improving-pixel-based-mim-by-reducing-wasted","title":"Improving Pixel-based MIM by Reducing Wasted Modeling Capability","date":"2023-08-01","arxiv_id":"2308.00261","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["open-mmlab/mmpretrain"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/predicting-masked-tokens-in-stochastic","slug":"predicting-masked-tokens-in-stochastic","title":"Stochastic positional embeddings improve masked image modeling","date":"2023-07-31","arxiv_id":"2308.00566","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["amirbar/stop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"handmim-pose-aware-self-supervised-learning","title":"HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation","date":"2023-07-29","arxiv_id":"2307.16061","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-nuclei-representations-with-masked","title":"Learning Nuclei Representations with Masked Image Modelling","date":"2023-06-29","arxiv_id":"2306.17116","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-distillation-connecting-masked","title":"Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners","date":"2023-06-28","arxiv_id":"2306.15876","n_code_links":0,"syntology":null},{"paper":"/paper/you-can-mask-more-for-extremely-low-bitrate","slug":"you-can-mask-more-for-extremely-low-bitrate","title":"You Can Mask More For Extremely Low-Bitrate Image Compression","date":"2023-06-27","arxiv_id":"2306.15561","n_code_links":1,"syntology":null},{"paper":"/paper/augmenting-sub-model-to-improve-main-model","slug":"augmenting-sub-model-to-improve-main-model","title":"Masking meets Supervision: A Strong Learning Alliance","date":"2023-06-20","arxiv_id":"2306.11339","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-across-decentralized-multi-modal","title":"Learning Across Decentralized Multi-Modal Remote Sensing Archives with Federated Learning","date":"2023-06-01","arxiv_id":"2306.00792","n_code_links":0,"syntology":null},{"paper":null,"slug":"delving-deeper-into-data-scaling-in-masked","title":"Delving Deeper into Data Scaling in Masked Image Modeling","date":"2023-05-24","arxiv_id":"2305.15248","n_code_links":0,"syntology":null},{"paper":"/paper/what-do-self-supervised-vision-transformers","slug":"what-do-self-supervised-vision-transformers","title":"What Do Self-Supervised Vision Transformers Learn?","date":"2023-05-01","arxiv_id":"2305.00729","n_code_links":1,"syntology":null},{"paper":null,"slug":"img2vec-a-teacher-of-high-token-diversity","title":"Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders","date":"2023-04-25","arxiv_id":"2304.12535","n_code_links":0,"syntology":null},{"paper":"/paper/fremae-fourier-transform-meets-masked","slug":"fremae-fourier-transform-meets-masked","title":"FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation","date":"2023-04-21","arxiv_id":"2304.10864","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-tuning-a-little-help-to-make","slug":"contrastive-tuning-a-little-help-to-make","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","date":"2023-04-20","arxiv_id":"2304.10520","n_code_links":1,"syntology":null},{"paper":"/paper/hard-patches-mining-for-masked-image-modeling","slug":"hard-patches-mining-for-masked-image-modeling","title":"Hard Patches Mining for Masked Image Modeling","date":"2023-04-12","arxiv_id":"2304.05919","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["haochen-wang409/hpm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixed-autoencoder-for-self-supervised-visual","slug":"mixed-autoencoder-for-self-supervised-visual","title":"Mixed Autoencoder for Self-supervised Visual Representation Learning","date":"2023-03-30","arxiv_id":"2303.17152","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/pmatch-paired-masked-image-modeling-for-dense","slug":"pmatch-paired-masked-image-modeling-for-dense","title":"PMatch: Paired Masked Image Modeling for Dense Geometric Matching","date":"2023-03-30","arxiv_id":"2303.17342","n_code_links":1,"syntology":{"ran":15,"of":21,"n_ran_checked":12,"n_instrument":3,"unverified":6,"pointer_only":21,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["shngjz/pmatch"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/hybridmim-a-hybrid-masked-image-modeling","slug":"hybridmim-a-hybrid-masked-image-modeling","title":"HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation","date":"2023-03-18","arxiv_id":"2303.10333","n_code_links":1,"syntology":null},{"paper":"/paper/deepmim-deep-supervision-for-masked-image","slug":"deepmim-deep-supervision-for-masked-image","title":"DeepMIM: Deep Supervision for Masked Image Modeling","date":"2023-03-15","arxiv_id":"2303.08817","n_code_links":1,"syntology":null},{"paper":"/paper/adpe-adversarial-positional-embeddings-for","slug":"adpe-adversarial-positional-embeddings-for","title":"AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+","date":"2023-03-14","arxiv_id":"2303.07598","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["maple-research-lab/AdPE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dppmask-masked-image-modeling-with","title":"DPPMask: Masked Image Modeling with Determinantal Point Processes","date":"2023-03-13","arxiv_id":"2303.12736","n_code_links":0,"syntology":null},{"paper":"/paper/masked-image-modeling-with-local-multi-scale","slug":"masked-image-modeling-with-local-multi-scale","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","date":"2023-03-09","arxiv_id":"2303.05251","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":10,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["huawei-noah/Efficient-Computing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/pixmim-rethinking-pixel-reconstruction-in","slug":"pixmim-rethinking-pixel-reconstruction-in","title":"PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling","date":"2023-03-04","arxiv_id":"2303.02416","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["open-mmlab/mmselfsup"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-masked-autoencoders-with-self","title":"Efficient Masked Autoencoders with Self-Consistency","date":"2023-02-28","arxiv_id":"2302.14431","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":150,"with_a_code_link":88,"where_syntology_ran_a_sample":31,"not_listed_spam_title":0,"listed":150,"listed_where_code_ran":31,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":31,"papers_where_code_ran_first_page":"/method/mim/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/mim/papers/2","json":"/method/mim/papers/2.json","rows":50},{"order":"ran","page":1,"of":1,"url":"/method/mim/papers/ran/1","json":"/method/mim/papers/ran/1.json","rows":31}],"tasks":[{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":53},{"task":"/task/representation-learning","name":"Representation Learning","papers":35},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":33},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":32},{"task":"/task/image-classification","name":"Image Classification","papers":23},{"task":"/task/object-detection","name":"Object Detection","papers":21},{"task":"/task/image-classification","name":"image-classification","papers":20},{"task":"/task/object-detection-1","name":"object-detection","papers":18},{"task":"/task/decoder","name":"Decoder","papers":12},{"task":"/task/language-modelling","name":"Language Modelling","papers":8},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":8},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":7},{"task":"/task/language-modeling","name":"Language Modeling","papers":7},{"task":"/task/attribute","name":"Attribute","papers":6},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":6},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":6},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":6},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":5},{"task":"/task/segmentation","name":"Segmentation","papers":5},{"task":"/task/self-supervised-image-classification","name":"Self-Supervised Image Classification","papers":5}],"tasks_shown":20,"n_tasks":165,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":5},{"year":"2021","papers":1},{"year":"2022","papers":35},{"year":"2023","papers":50},{"year":"2024","papers":40},{"year":"2025","papers":18}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mim"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=MIM","read_at":"2026-10-05T00:59:07+00:00","query":"MIM","kind":"paper","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1910.03175","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":3,"served":null,"leading_other_bearer":{"arxiv_id":"2006.04146","title":"MIM: A deep mixed residual method for solving high-order partial differential equations","citations":126,"named_by":["title_prefix"],"bearer_name":"MIM: A deep mixed residual method for solving high-order partial differential equations","ask_with":"have('2006.04146')"},"n_other_bearers_listed":3,"note":"Nothing resolved to 'MIM' by name, but 3 thing(s) here DECLARE that name -- most cited: the paper 'MIM: A deep mixed residual method for solving high-order partial differential equations' (arXiv:2006.04146, 126 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 3 entries in Syntology's graph carry it; the most cited is the paper “MIM: A deep mixed residual method for solving high-order partial differential equations” (arXiv:2006.04146, 126 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":["MiM-MU","MIM-Refiner","decision-based MIM"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"395ff36539076a6a5524d4fc860afe63487a42d158fbd0350cb02ff1b625c4f1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}