{"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/relu6","slug":"relu6","name":"ReLU6","full_name":"ReLU6","full_name_withheld":false,"description_markdown":"**ReLU6** is a modification of the [rectified linear unit](https://paperswithcode.com/method/relu) where we limit the activation to a maximum size of $6$. This is due to increased robustness when used with low-precision computation.\r\n\r\nImage Credit: [PyTorch](https://pytorch.org/docs/master/generated/torch.nn.ReLU6.html)","description_state":"present","introduced_year":null,"introduced_by":{"title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","paper":"/paper/mobilenets-efficient-convolutional-neural","first_author":"Andrew G. Howard","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mobilenets-efficient-convolutional-neural"},"source":{"url":"http://arxiv.org/abs/1704.04861v1","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/pytorch/blob/96aaa311c0251d24decb9dc5da4957b7c590af6f/torch/nn/modules/activation.py#L246","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Activation Functions","url":"/methods/category/activation-functions","pwc_aliases":[]}],"n_papers_tagged":95,"archive_num_papers":95,"papers_newest_first":[{"paper":null,"slug":"comparative-analysis-of-lightweight-deep","title":"Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices","date":"2025-05-06","arxiv_id":"2505.03303","n_code_links":0,"syntology":null},{"paper":null,"slug":"velu-variance-enhanced-learning-unit-for-deep","title":"VeLU: Variance-enhanced Learning Unit for Deep Neural Networks","date":"2025-04-21","arxiv_id":"2504.15051","n_code_links":0,"syntology":null},{"paper":null,"slug":"time-frequency-analysis-of-emg-signal-for","title":"Time Frequency Analysis of EMG Signal for Gesture Recognition using Fine grained Features","date":"2025-04-20","arxiv_id":"2504.14708","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-light-perspective-for-3d-object-detection","title":"A Light Perspective for 3D Object Detection","date":"2025-03-10","arxiv_id":"2503.07133","n_code_links":0,"syntology":null},{"paper":null,"slug":"pulmonary-tuberculosis-edge-diagnosis-system","title":"Pulmonary Tuberculosis Edge Diagnosis System Based on MindSpore Framework: Low-cost and High-precision Implementation with Ascend 310 Chip","date":"2025-02-15","arxiv_id":"2502.14885","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypercam-low-power-onboard-computer-vision","title":"HyperCam: Low-Power Onboard Computer Vision for IoT Cameras","date":"2025-01-17","arxiv_id":"2501.10547","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-communication-with-deep","title":"Revolutionizing Communication with Deep Learning and XAI for Enhanced Arabic Sign Language Recognition","date":"2025-01-14","arxiv_id":"2501.08169","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-forward-forward-algorithm","title":"Scalable Forward-Forward Algorithm","date":"2025-01-06","arxiv_id":"2501.03176","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-imc-accelerator-design","title":"Towards Efficient IMC Accelerator Design Through Joint Hardware-Workload Co-optimization","date":"2024-10-22","arxiv_id":"2410.16759","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-deep-learning-board-training","title":"Efficient Deep Learning Board: Training Feedback Is Not All You Need","date":"2024-10-17","arxiv_id":"2410.14743","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-monitoring-of-lower-limb-movement","title":"Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learning","date":"2024-10-13","arxiv_id":"2410.19769","n_code_links":0,"syntology":null},{"paper":null,"slug":"pomonag-pareto-optimal-many-objective-neural","title":"POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator","date":"2024-09-30","arxiv_id":"2409.20447","n_code_links":0,"syntology":null},{"paper":"/paper/rnc-efficient-rram-aware-nas-and-compilation","slug":"rnc-efficient-rram-aware-nas-and-compilation","title":"RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices","date":"2024-09-27","arxiv_id":"2409.18841","n_code_links":1,"syntology":null},{"paper":"/paper/plainusr-chasing-faster-convnet-for-efficient","slug":"plainusr-chasing-faster-convnet-for-efficient","title":"PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution","date":"2024-09-20","arxiv_id":"2409.13435","n_code_links":1,"syntology":null},{"paper":null,"slug":"watermas-sharpness-aware-maximization-for","title":"WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking","date":"2024-09-05","arxiv_id":"2409.03902","n_code_links":0,"syntology":null},{"paper":"/paper/analysis-of-modern-computer-vision-models-for","slug":"analysis-of-modern-computer-vision-models-for","title":"Analysis of Modern Computer Vision Models for Blood Cell Classification","date":"2024-06-30","arxiv_id":"2407.00759","n_code_links":1,"syntology":null},{"paper":"/paper/hass-hardware-aware-sparsity-search-for","slug":"hass-hardware-aware-sparsity-search-for","title":"HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator","date":"2024-06-05","arxiv_id":"2406.03088","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-based-approach-for-food-weight","title":"Vision-Based Approach for Food Weight Estimation from 2D Images","date":"2024-05-26","arxiv_id":"2405.16478","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-synthetic-images-on-morphing-attack","title":"Impact of Synthetic Images on Morphing Attack Detection Using a Siamese Network","date":"2024-03-14","arxiv_id":"2403.09380","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-machine-learning-dataset-of-bulldog","title":"A New Machine Learning Dataset of Bulldog Nostril Images for Stenosis Degree Classification","date":"2024-03-11","arxiv_id":"2403.07132","n_code_links":0,"syntology":null},{"paper":"/paper/multi-objective-differentiable-neural","slug":"multi-objective-differentiable-neural","title":"Multi-objective Differentiable Neural Architecture Search","date":"2024-02-28","arxiv_id":"2402.18213","n_code_links":1,"syntology":null},{"paper":null,"slug":"model-evaluation-for-domain-identification-of","title":"Model Evaluation for Domain Identification of Unknown Classes in Open-World Recognition: A Proposal","date":"2023-12-09","arxiv_id":"2312.05454","n_code_links":0,"syntology":null},{"paper":"/paper/learning-cortical-anomaly-through-masked","slug":"learning-cortical-anomaly-through-masked","title":"Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping","date":"2023-12-05","arxiv_id":"2312.02762","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-reusable-ai-enabled-defect-detection-system","title":"A Reusable AI-Enabled Defect Detection System for Railway Using Ensembled CNN","date":"2023-11-24","arxiv_id":"2311.14824","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-modified-deep-learning-models-in","title":"Unleashing Modified Deep Learning Models in Efficient COVID19 Detection","date":"2023-10-21","arxiv_id":"2310.14081","n_code_links":0,"syntology":null},{"paper":null,"slug":"ohq-on-chip-hardware-aware-quantization","title":"On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks","date":"2023-09-05","arxiv_id":"2309.01945","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-lightweight-and-accurate-face-detection","title":"A Lightweight and Accurate Face Detection Algorithm Based on Retinaface","date":"2023-08-08","arxiv_id":"2308.04340","n_code_links":0,"syntology":null},{"paper":"/paper/repvit-revisiting-mobile-cnn-from-vit","slug":"repvit-revisiting-mobile-cnn-from-vit","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","date":"2023-07-18","arxiv_id":"2307.09283","n_code_links":8,"syntology":{"ran":6,"of":12,"n_ran_checked":3,"n_instrument":3,"unverified":6,"pointer_only":5,"phrase":"6 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; 3 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/efficient-and-fully-automatic-retinal-choroid","slug":"efficient-and-fully-automatic-retinal-choroid","title":"An open-source deep learning algorithm for efficient and fully-automatic analysis of the choroid in optical coherence tomography","date":"2023-07-03","arxiv_id":"2307.00904","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-neural-network-compression-via","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","date":"2023-06-09","arxiv_id":"2306.05785","n_code_links":0,"syntology":null},{"paper":"/paper/diffusionnag-task-guided-neural-architecture","slug":"diffusionnag-task-guided-neural-architecture","title":"DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models","date":"2023-05-26","arxiv_id":"2305.16943","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cownowan/diffusionnag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"augmented-random-search-for-multi-objective","title":"Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML","date":"2023-05-23","arxiv_id":"2305.14109","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-classification-of-stroke-blood-clot","title":"Advancing Ischemic Stroke Diagnosis: A Novel Two-Stage Approach for Blood Clot Origin Identification","date":"2023-04-26","arxiv_id":"2304.13775","n_code_links":0,"syntology":null},{"paper":"/paper/layernas-neural-architecture-search-in","slug":"layernas-neural-architecture-search-in","title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","date":"2023-04-23","arxiv_id":"2304.11517","n_code_links":0,"syntology":null},{"paper":"/paper/reinforce-data-multiply-impact-improved-model","slug":"reinforce-data-multiply-impact-improved-model","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","date":"2023-03-15","arxiv_id":"2303.08983","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-general-purpose-transferable-predictor-for","title":"A General-Purpose Transferable Predictor for Neural Architecture Search","date":"2023-02-21","arxiv_id":"2302.10835","n_code_links":0,"syntology":null},{"paper":"/paper/trainable-activations-for-image","slug":"trainable-activations-for-image","title":"Trainable Activations for Image Classification","date":"2023-01-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/m3e-yolo-a-new-lightweight-network-for","slug":"m3e-yolo-a-new-lightweight-network-for","title":"M3E-Yolo: A New Lightweight Network for Traffic Sign Recognition","date":"2023-01-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mobiletl-on-device-transfer-learning-with","title":"MobileTL: On-device Transfer Learning with Inverted Residual Blocks","date":"2022-12-05","arxiv_id":"2212.03246","n_code_links":0,"syntology":null},{"paper":null,"slug":"receptive-field-refinement-for-convolutional","title":"Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance","date":"2022-11-26","arxiv_id":"2211.14487","n_code_links":0,"syntology":null},{"paper":"/paper/repghost-a-hardware-efficient-ghost-module","slug":"repghost-a-hardware-efficient-ghost-module","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","date":"2022-11-11","arxiv_id":"2211.06088","n_code_links":3,"syntology":{"ran":10,"of":17,"n_ran_checked":6,"n_instrument":4,"unverified":7,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["chengpengchen/repghost","rwightman/pytorch-image-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-large-scale-audio-tagging-via","slug":"efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fschmid56/efficientat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vitruvio-3d-building-meshes-via-single","slug":"vitruvio-3d-building-meshes-via-single","title":"Vitruvio: 3D Building Meshes via Single Perspective Sketches","date":"2022-10-24","arxiv_id":"2210.13634","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-network-compression-by-joint-sparsity","title":"Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction","date":"2022-10-14","arxiv_id":"2210.07451","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiclass-asma-vs-targeted-pgd-attack-in","title":"Multiclass ASMA vs Targeted PGD Attack in Image Segmentation","date":"2022-08-03","arxiv_id":"2208.01844","n_code_links":0,"syntology":null},{"paper":"/paper/a-real-time-fire-segmentation-method-based-on","slug":"a-real-time-fire-segmentation-method-based-on","title":"A Real-time Fire Segmentation Method Based on A Deep Learning Approach","date":"2022-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-lightweight-identification-of","title":"Improved lightweight identification of agricultural diseases based on MobileNetV3","date":"2022-07-19","arxiv_id":"2207.11238","n_code_links":0,"syntology":null},{"paper":"/paper/grouped-pointwise-convolutions-reduce","slug":"grouped-pointwise-convolutions-reduce","title":"Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks","date":"2022-06-30","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"mushroom-image-recognition-and-distance","title":"Mushroom image recognition and distance generation based on attention-mechanism model and genetic information","date":"2022-06-27","arxiv_id":"2206.13383","n_code_links":0,"syntology":null},{"paper":"/paper/bag-of-tricks-for-long-tail-visual","slug":"bag-of-tricks-for-long-tail-visual","title":"Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images","date":"2022-06-24","arxiv_id":"2206.12458","n_code_links":1,"syntology":null},{"paper":"/paper/mocovit-mobile-convolutional-vision","slug":"mocovit-mobile-convolutional-vision","title":"MoCoViT: Mobile Convolutional Vision Transformer","date":"2022-05-25","arxiv_id":"2205.12635","n_code_links":1,"syntology":null},{"paper":null,"slug":"novel-multicolumn-kernel-extreme-learning","title":"Novel Multicolumn Kernel Extreme Learning Machine for Food Detection via Optimal Features from CNN","date":"2022-05-15","arxiv_id":"2205.07348","n_code_links":0,"syntology":null},{"paper":"/paper/hierattn-effectively-learn-representations","slug":"hierattn-effectively-learn-representations","title":"Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention","date":"2022-05-09","arxiv_id":"2205.04326","n_code_links":2,"syntology":null},{"paper":"/paper/topformer-token-pyramid-transformer-for","slug":"topformer-token-pyramid-transformer-for","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","date":"2022-04-12","arxiv_id":"2204.05525","n_code_links":3,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["hustvl/TopFormer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/overcoming-oscillations-in-quantization-aware","slug":"overcoming-oscillations-in-quantization-aware","title":"Overcoming Oscillations in Quantization-Aware Training","date":"2022-03-21","arxiv_id":"2203.11086","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["qualcomm-ai-research/oscillations-qat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"a-hardware-aware-system-for-accelerating-deep","title":"A Hardware-Aware System for Accelerating Deep Neural Network Optimization","date":"2022-02-25","arxiv_id":"2202.12954","n_code_links":0,"syntology":null},{"paper":"/paper/condensenext-an-ultra-efficient-deep-neural","slug":"condensenext-an-ultra-efficient-deep-neural","title":"CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems","date":"2021-12-01","arxiv_id":"2112.00698","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simple-approach-to-image-tilt-correction","title":"A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones","date":"2021-10-31","arxiv_id":"2111.00398","n_code_links":0,"syntology":null},{"paper":"/paper/mobilevit-light-weight-general-purpose-and","slug":"mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","arxiv_id":"2110.02178","n_code_links":31,"syntology":{"ran":53,"of":68,"n_ran_checked":44,"n_instrument":9,"unverified":15,"pointer_only":18,"phrase":"53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified","official":{"repos":["apple/ml-cvnets"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/hybrid-cloud-edge-networks-for-efficient","slug":"hybrid-cloud-edge-networks-for-efficient","title":"Hybrid Cloud-Edge Networks for Efficient Inference","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"l-2-nas-learning-to-optimize-neural","title":"L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning","date":"2021-09-25","arxiv_id":"2109.12425","n_code_links":0,"syntology":null},{"paper":"/paper/ligar-lightweight-general-purpose-action","slug":"ligar-lightweight-general-purpose-action","title":"LIGAR: Lightweight General-purpose Action Recognition","date":"2021-08-30","arxiv_id":"2108.13153","n_code_links":1,"syntology":null},{"paper":"/paper/micronet-improving-image-recognition-with","slug":"micronet-improving-image-recognition-with","title":"MicroNet: Improving Image Recognition with Extremely Low FLOPs","date":"2021-08-12","arxiv_id":"2108.05894","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":8,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["liyunsheng13/micronet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-former-bridging-mobilenet-and","slug":"mobile-former-bridging-mobilenet-and","title":"Mobile-Former: Bridging MobileNet and Transformer","date":"2021-08-12","arxiv_id":"2108.05895","n_code_links":4,"syntology":null},{"paper":"/paper/bias-loss-for-mobile-neural-networks","slug":"bias-loss-for-mobile-neural-networks","title":"Bias Loss for Mobile Neural Networks","date":"2021-07-23","arxiv_id":"2107.11170","n_code_links":2,"syntology":null},{"paper":null,"slug":"automated-age-related-macular-degeneration","title":"Automated age-related macular degeneration area estimation -- first results","date":"2021-07-05","arxiv_id":"2107.02211","n_code_links":0,"syntology":null},{"paper":"/paper/rapid-neural-architecture-search-by-learning-1","slug":"rapid-neural-architecture-search-by-learning-1","title":"Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets","date":"2021-07-02","arxiv_id":"2107.00860","n_code_links":1,"syntology":{"ran":12,"of":19,"n_ran_checked":11,"n_instrument":1,"unverified":7,"pointer_only":6,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["HayeonLee/MetaD2A"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"paper":"/paper/encoder-decoder-architectures-for-clinically","slug":"encoder-decoder-architectures-for-clinically","title":"Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation","date":"2021-06-21","arxiv_id":"2106.11447","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-care-label-concept-a-certification-suite","title":"The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning","date":"2021-06-01","arxiv_id":"2106.00512","n_code_links":0,"syntology":null},{"paper":"/paper/blurs-make-results-clearer-spatial-smoothings","slug":"blurs-make-results-clearer-spatial-smoothings","title":"Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness","date":"2021-05-26","arxiv_id":"2105.12639","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xxxnell/spatial-smoothing"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"learning-mobile-cnn-feature-extraction-toward","title":"Learning Mobile CNN Feature Extraction Toward Fast Computation of Visual Object Tracking","date":"2021-04-03","arxiv_id":"2104.01381","n_code_links":0,"syntology":null},{"paper":"/paper/levit-a-vision-transformer-in-convnet-s","slug":"levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","arxiv_id":"2104.01136","n_code_links":12,"syntology":{"ran":23,"of":30,"n_ran_checked":21,"n_instrument":2,"unverified":7,"pointer_only":0,"phrase":"23 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["facebookresearch/LeViT","rwightman/pytorch-image-models"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/one-shot-neural-ensemble-architecture-search","slug":"one-shot-neural-ensemble-architecture-search","title":"One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking","date":"2021-04-01","arxiv_id":"2104.00597","n_code_links":1,"syntology":null},{"paper":null,"slug":"netadaptv2-efficient-neural-architecture","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","date":"2021-03-31","arxiv_id":"2104.00031","n_code_links":0,"syntology":null},{"paper":null,"slug":"cascade-weight-shedding-in-deep-neural","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","date":"2021-03-19","arxiv_id":"2103.10629","n_code_links":0,"syntology":null},{"paper":"/paper/hr-depth-high-resolution-self-supervised","slug":"hr-depth-high-resolution-self-supervised","title":"HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation","date":"2020-12-14","arxiv_id":"2012.07356","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shawLyu/HR-Depth"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/model-rubiks-cube-twisting-resolution-depth","slug":"model-rubiks-cube-twisting-resolution-depth","title":"Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets","date":"2020-12-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":null,"slug":"micronet-towards-image-recognition-with","title":"MicroNet: Towards Image Recognition with Extremely Low FLOPs","date":"2020-11-24","arxiv_id":"2011.12289","n_code_links":0,"syntology":null},{"paper":"/paper/multigrid-in-channels-neural-network","slug":"multigrid-in-channels-neural-network","title":"MGIC: Multigrid-in-Channels Neural Network Architectures","date":"2020-11-17","arxiv_id":"2011.09128","n_code_links":1,"syntology":null},{"paper":"/paper/cream-of-the-crop-distilling-prioritized","slug":"cream-of-the-crop-distilling-prioritized","title":"Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search","date":"2020-10-29","arxiv_id":"2010.15821","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["microsoft/cream"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/model-rubik-s-cube-twisting-resolution-depth","slug":"model-rubik-s-cube-twisting-resolution-depth","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","date":"2020-10-28","arxiv_id":"2010.14819","n_code_links":9,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/CV-backbones","huawei-noah/ghostnet"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/once-quantized-for-all-progressively-1","slug":"once-quantized-for-all-progressively-1","title":"Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search","date":"2020-10-09","arxiv_id":"2010.04354","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-soccer-balls-with-reduced-neural","slug":"detecting-soccer-balls-with-reduced-neural","title":"Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios","date":"2020-09-28","arxiv_id":"2009.13684","n_code_links":1,"syntology":null},{"paper":null,"slug":"discovering-multi-hardware-mobile-models-via","title":"Discovering Multi-Hardware Mobile Models via Architecture Search","date":"2020-08-18","arxiv_id":"2008.08178","n_code_links":0,"syntology":null},{"paper":"/paper/pareco-pareto-aware-channel-optimization-for","slug":"pareco-pareto-aware-channel-optimization-for","title":"Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks","date":"2020-07-23","arxiv_id":"2007.11752","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["cmu-enyac/Joslim"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/fine-grained-stochastic-architecture-search","slug":"fine-grained-stochastic-architecture-search","title":"Fine-Grained Stochastic Architecture Search","date":"2020-06-17","arxiv_id":"2006.09581","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/efficient-model-for-image-classification-with","slug":"efficient-model-for-image-classification-with","title":"Efficient Model for Image Classification With Regularization Tricks","date":"2020-02-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ghostnet-more-features-from-cheap-operations","slug":"ghostnet-more-features-from-cheap-operations","title":"GhostNet: More Features from Cheap Operations","date":"2019-11-27","arxiv_id":"1911.11907","n_code_links":33,"syntology":{"ran":19,"of":23,"n_ran_checked":16,"n_instrument":3,"unverified":4,"pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["huawei-noah/ghostnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"structured-multi-hashing-for-model","title":"Structured Multi-Hashing for Model Compression","date":"2019-11-25","arxiv_id":"1911.11177","n_code_links":0,"syntology":null},{"paper":"/paper/panoptic-deeplab-a-simple-strong-and-fast","slug":"panoptic-deeplab-a-simple-strong-and-fast","title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","date":"2019-11-22","arxiv_id":"1911.10194","n_code_links":9,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["bowenc0221/panoptic-deeplab"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"paper":"/paper/street-crossing-aid-using-light-weight-cnns","slug":"street-crossing-aid-using-light-weight-cnns","title":"Street Crossing Aid Using Light-weight CNNs for the Visually Impaired","date":"2019-09-14","arxiv_id":"1909.09598","n_code_links":1,"syntology":null},{"paper":"/paper/moga-searching-beyond-mobilenetv3","slug":"moga-searching-beyond-mobilenetv3","title":"MoGA: Searching Beyond MobileNetV3","date":"2019-08-04","arxiv_id":"1908.01314","n_code_links":2,"syntology":null},{"paper":"/paper/butterfly-transform-an-efficient-fft-based","slug":"butterfly-transform-an-efficient-fft-based","title":"Butterfly Transform: An Efficient FFT Based Neural Architecture Design","date":"2019-06-05","arxiv_id":"1906.02256","n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-mobilenetv3","slug":"searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","n_code_links":67,"syntology":{"ran":86,"of":105,"n_ran_checked":75,"n_instrument":11,"unverified":19,"pointer_only":46,"phrase":"86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 9 honoured, 2 violated, 64 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":null}},{"paper":"/paper/mobilenetv2-inverted-residuals-and-linear","slug":"mobilenetv2-inverted-residuals-and-linear","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","date":"2018-01-13","arxiv_id":"1801.04381","n_code_links":159,"syntology":{"ran":85,"of":111,"n_ran_checked":64,"n_instrument":21,"unverified":26,"pointer_only":64,"phrase":"85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified","official":null}}],"papers_shown":95,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":95,"with_a_code_link":50,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":95,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":18,"papers_where_code_ran_first_page":"/method/relu6/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":"ran","page":1,"of":1,"url":"/method/relu6/papers/ran/1","json":"/method/relu6/papers/ran/1.json","rows":18}],"tasks":[{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":20},{"task":"/task/image-classification","name":"Image Classification","papers":19},{"task":"/task/object-detection","name":"Object Detection","papers":11},{"task":"/task/image-classification","name":"image-classification","papers":11},{"task":"/task/object-detection-1","name":"object-detection","papers":9},{"task":"/task/segmentation","name":"Segmentation","papers":7},{"task":"/task/classification-1","name":"Classification","papers":6},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":6},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/quantization","name":"Quantization","papers":6},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":6},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":6},{"task":null,"name":"CPU","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/automl","name":"AutoML","papers":3},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":3},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":null,"name":"GPU","papers":3},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":3},{"task":"/task/diagnostic","name":"Diagnostic","papers":2}],"tasks_shown":20,"n_tasks":95,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":7},{"year":"2020","papers":12},{"year":"2021","papers":19},{"year":"2022","papers":18},{"year":"2023","papers":17},{"year":"2024","papers":13},{"year":"2025","papers":8}],"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/relu6"},"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=ReLU6","read_at":"2026-10-05T01:01:05+00:00","query":"ReLU6","kind":"method","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":"1704.04861","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'ReLU6' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"8a58fd812f57575a4977dcc53fd57da5a98a036a6adc439b6663b6a31b147836","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}