{"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/focal-loss","slug":"focal-loss","name":"Focal Loss","full_name":"Focal Loss","full_name_withheld":false,"description_markdown":"A **Focal Loss** function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to focus learning on hard misclassified examples. It is a dynamically scaled cross entropy loss, where the scaling factor decays to zero as confidence in the correct class increases. Intuitively, this scaling factor can automatically down-weight the contribution of easy examples during training and rapidly focus the model on hard examples. \r\n\r\nFormally, the Focal Loss adds a factor $(1 - p\\_{t})^\\gamma$ to the standard cross entropy criterion. Setting $\\gamma>0$ reduces the relative loss for well-classified examples ($p\\_{t}>.5$), putting more focus on hard, misclassified examples. Here there is tunable *focusing* parameter $\\gamma \\ge 0$. \r\n\r\n$$ {\\text{FL}(p\\_{t}) = - (1 - p\\_{t})^\\gamma \\log\\left(p\\_{t}\\right)} $$","description_state":"present","introduced_year":null,"introduced_by":{"title":"Focal Loss for Dense Object Detection","paper":"/paper/focal-loss-for-dense-object-detection","first_author":"Tsung-Yi Lin","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/focal-loss-for-dense-object-detection"},"source":{"url":"http://arxiv.org/abs/1708.02002v2","title":"Focal Loss for Dense Object Detection","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/clcarwin/focal_loss_pytorch/blob/e11e75bad957aecf641db6998a1016204722c1bb/focalloss.py#L6","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":461,"archive_num_papers":462,"papers_newest_first":[{"paper":null,"slug":"lumicrs-asymmetric-contrastive-prototype","title":"LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Movie Recommendation","date":"2025-07-07","arxiv_id":"2507.04722","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-reweighted-risk-for-calibration","title":"Revisiting Reweighted Risk for Calibration: AURC, Focal Loss, and Inverse Focal Loss","date":"2025-05-29","arxiv_id":"2505.23463","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-class-incremental-learning-for","title":"Few-Shot Class-Incremental Learning For Efficient SAR Automatic Target Recognition","date":"2025-05-26","arxiv_id":"2505.19565","n_code_links":0,"syntology":null},{"paper":null,"slug":"panicar-securing-the-perception-of-advanced","title":"PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting","date":"2025-05-08","arxiv_id":"2505.05183","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-audio-deepfake-detection-from-raw","slug":"end-to-end-audio-deepfake-detection-from-raw","title":"End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation","date":"2025-04-29","arxiv_id":"2504.20923","n_code_links":1,"syntology":null},{"paper":null,"slug":"comprehensive-evaluation-of-quantitative","title":"Comprehensive Evaluation of Quantitative Measurements from Automated Deep Segmentations of PSMA PET/CT Images","date":"2025-04-22","arxiv_id":"2504.16237","n_code_links":0,"syntology":null},{"paper":null,"slug":"class-imbalance-correction-for-improved","title":"Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT","date":"2025-04-08","arxiv_id":"2504.05591","n_code_links":0,"syntology":null},{"paper":"/paper/uncertainty-weighted-gradients-for-model","slug":"uncertainty-weighted-gradients-for-model","title":"Uncertainty Weighted Gradients for Model Calibration","date":"2025-03-26","arxiv_id":"2503.22725","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 1 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":{"repos":["Jinxu-Lin/BSCE-GRA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-adaptive-gamma-context-aware-ssm-based","title":"Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection","date":"2025-03-03","arxiv_id":"2503.01234","n_code_links":0,"syntology":null},{"paper":"/paper/dur360bev-a-real-world-single-360-degree","slug":"dur360bev-a-real-world-single-360-degree","title":"Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving","date":"2025-03-02","arxiv_id":"2503.00675","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Tom-E-Durham/Dur360BEV","Tom-E-Durham/icra2025-dur360bev"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fast-cos-a-fast-one-stage-object-detector","title":"Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving","date":"2025-02-11","arxiv_id":"2502.07417","n_code_links":0,"syntology":null},{"paper":null,"slug":"supervised-contrastive-learning-for-cell","title":"Supervised contrastive learning for cell stage classification of animal embryos","date":"2025-02-11","arxiv_id":"2502.07360","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-voxel-weighted-loss-using-l1-norms","slug":"adaptive-voxel-weighted-loss-using-l1-norms","title":"Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images","date":"2025-02-04","arxiv_id":"2502.02756","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-powered-classification-of","title":"Deep Learning-Powered Classification of Thoracic Diseases in Chest X-Rays","date":"2025-01-24","arxiv_id":"2501.14279","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-scale-aware-adaptive-masked-knowledge","title":"Dual Scale-aware Adaptive Masked Knowledge Distillation for Object Detection","date":"2025-01-13","arxiv_id":"2501.07101","n_code_links":0,"syntology":null},{"paper":null,"slug":"focalpo-enhancing-preference-optimizing-by","title":"FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings","date":"2025-01-11","arxiv_id":"2501.06645","n_code_links":0,"syntology":null},{"paper":null,"slug":"influences-on-llm-calibration-a-study-of","title":"Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles","date":"2025-01-07","arxiv_id":"2501.03991","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-boundary-loss-for-the-hierarchical","slug":"exploiting-boundary-loss-for-the-hierarchical","title":"Exploiting Boundary Loss for the Hierarchical Panoptic Segmentation of Plants and Leaves","date":"2024-12-31","arxiv_id":"2501.00527","n_code_links":1,"syntology":null},{"paper":"/paper/detection-of-body-packs-in-abdominal-ct-scans","slug":"detection-of-body-packs-in-abdominal-ct-scans","title":"Detection of Body Packs in Abdominal CT scans Through Artificial Intelligence","date":"2024-12-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/distortion-aware-adversarial-attacks-on","slug":"distortion-aware-adversarial-attacks-on","title":"Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors","date":"2024-12-25","arxiv_id":"2412.18815","n_code_links":1,"syntology":null},{"paper":"/paper/emov2-pushing-5m-vision-model-frontier","slug":"emov2-pushing-5m-vision-model-frontier","title":"EMOv2: Pushing 5M Vision Model Frontier","date":"2024-12-09","arxiv_id":"2412.06674","n_code_links":1,"syntology":null},{"paper":"/paper/psych-occlusion-using-visual-psychophysics","slug":"psych-occlusion-using-visual-psychophysics","title":"Psych-Occlusion: Using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescue","date":"2024-12-07","arxiv_id":"2412.05553","n_code_links":1,"syntology":null},{"paper":"/paper/ocdet-object-center-detection-via-bounding","slug":"ocdet-object-center-detection-via-bounding","title":"OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs","date":"2024-11-23","arxiv_id":"2411.15653","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-adaptive-hybrid-focal-entropy-loss","title":"A Novel Adaptive Hybrid Focal-Entropy Loss for Enhancing Diabetic Retinopathy Detection Using Convolutional Neural Networks","date":"2024-11-16","arxiv_id":"2411.10843","n_code_links":0,"syntology":null},{"paper":"/paper/normative-modeling-for-ad-diagnosis-and","slug":"normative-modeling-for-ad-diagnosis-and","title":"Normative Modeling for AD Diagnosis and Biomarker Identification","date":"2024-11-15","arxiv_id":"2411.10570","n_code_links":1,"syntology":null},{"paper":null,"slug":"1-800-shared-tasks-nlu-of-devanagari-script","title":"1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs","date":"2024-11-11","arxiv_id":"2411.06850","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-stage-tfs-thai-one-stage-fingerspelling","title":"One-Stage-TFS: Thai One-Stage Fingerspelling Dataset for Fingerspelling Recognition Frameworks","date":"2024-11-05","arxiv_id":"2411.02768","n_code_links":0,"syntology":null},{"paper":"/paper/divergent-domains-convergent-grading","slug":"divergent-domains-convergent-grading","title":"Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading","date":"2024-11-04","arxiv_id":"2411.02614","n_code_links":1,"syntology":null},{"paper":null,"slug":"bit-mamsleep-bidirectional-temporal-mamba-for","title":"BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep Staging","date":"2024-11-03","arxiv_id":"2411.01589","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-omra-fast-online-motion-resolution","title":"Fast-OMRA: Fast Online Motion Resolution Adaptation for Neural B-Frame Coding","date":"2024-10-29","arxiv_id":"2410.21763","n_code_links":0,"syntology":null},{"paper":null,"slug":"calibrating-deep-neural-network-using","title":"Calibrating Deep Neural Network using Euclidean Distance","date":"2024-10-23","arxiv_id":"2410.18321","n_code_links":0,"syntology":null},{"paper":null,"slug":"attcdcnet-attention-enhanced-chest-disease","title":"AttCDCNet: Attention-enhanced Chest Disease Classification using X-Ray Images","date":"2024-10-20","arxiv_id":"2410.15437","n_code_links":0,"syntology":null},{"paper":"/paper/devil-in-the-tail-a-multi-modal-framework-for","slug":"devil-in-the-tail-a-multi-modal-framework-for","title":"Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction","date":"2024-10-16","arxiv_id":"2410.12249","n_code_links":1,"syntology":null},{"paper":null,"slug":"implicit-to-explicit-entropy-regularization","title":"Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels","date":"2024-10-05","arxiv_id":"2410.04256","n_code_links":0,"syntology":null},{"paper":"/paper/explicitly-modeling-pre-cortical-vision-with","slug":"explicitly-modeling-pre-cortical-vision-with","title":"Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness","date":"2024-09-25","arxiv_id":"2409.16838","n_code_links":1,"syntology":null},{"paper":null,"slug":"small-data-deep-learning-methodology-for-in","title":"Small data deep learning methodology for in-field disease detection","date":"2024-09-25","arxiv_id":"2409.17119","n_code_links":0,"syntology":null},{"paper":"/paper/autopet-challenge-iii-testing-the-robustness","slug":"autopet-challenge-iii-testing-the-robustness","title":"AutoPET Challenge III: Testing the Robustness of Generalized Dice Focal Loss trained 3D Residual UNet for FDG and PSMA Lesion Segmentation from Whole-Body PET/CT Images","date":"2024-09-16","arxiv_id":"2409.10151","n_code_links":2,"syntology":null},{"paper":null,"slug":"lithohod-a-litho-simulator-powered-framework","title":"LithoHoD: A Litho Simulator-Powered Framework for IC Layout Hotspot Detection","date":"2024-09-16","arxiv_id":"2409.10021","n_code_links":0,"syntology":null},{"paper":"/paper/reg-refined-generalized-focal-loss-for-road","slug":"reg-refined-generalized-focal-loss-for-road","title":"REG: Refined Generalized Focal Loss for Road Asset Detection on Thai Highways Using Vision-Based Detection and Segmentation Models","date":"2024-09-15","arxiv_id":"2409.09877","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalized-knowledge-tracing-through","title":"Personalized Knowledge Tracing through Student Representation Reconstruction and Class Imbalance Mitigation","date":"2024-09-10","arxiv_id":"2409.06745","n_code_links":0,"syntology":null},{"paper":null,"slug":"renormalized-connection-for-scale-preferred","title":"Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery","date":"2024-09-09","arxiv_id":"2409.05624","n_code_links":0,"syntology":null},{"paper":null,"slug":"lung-detr-deformable-detection-transformer","title":"Lung-DETR: Deformable Detection Transformer for Sparse Lung Nodule Anomaly Detection","date":"2024-09-08","arxiv_id":"2409.05200","n_code_links":0,"syntology":null},{"paper":"/paper/classification-of-epileptic-seizures-in-eeg","slug":"classification-of-epileptic-seizures-in-eeg","title":"Classification of epileptic seizures in EEG data based on iterative gated graph convolution network","date":"2024-08-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-license-plate-super-resolution-a","slug":"enhancing-license-plate-super-resolution-a","title":"Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach","date":"2024-08-27","arxiv_id":"2408.15103","n_code_links":1,"syntology":null},{"paper":"/paper/improving-calibration-by-relating-focal-loss","slug":"improving-calibration-by-relating-focal-loss","title":"Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness","date":"2024-08-21","arxiv_id":"2408.11598","n_code_links":1,"syntology":null},{"paper":"/paper/2408-02674","slug":"2408-02674","title":"On Feasibility of Intent Obfuscating Attacks","date":"2024-07-22","arxiv_id":"2408.02674","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-semantic-segmentation-with-adaptive","title":"Enhancing Semantic Segmentation with Adaptive Focal Loss: A Novel Approach","date":"2024-07-13","arxiv_id":"2407.09828","n_code_links":0,"syntology":null},{"paper":"/paper/poisson-ordinal-network-for-gleason-group","slug":"poisson-ordinal-network-for-gleason-group","title":"Poisson Ordinal Network for Gleason Group Estimation Using Bi-Parametric MRI","date":"2024-07-08","arxiv_id":"2407.05796","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalised-outfit-recommendation-via","title":"Personalised Outfit Recommendation via History-aware Transformers","date":"2024-06-29","arxiv_id":"2407.00289","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-utilize-gradient-information-for","title":"Learning to utilize image second-order derivative information for crisp edge detection","date":"2024-06-09","arxiv_id":"2406.05779","n_code_links":0,"syntology":null},{"paper":"/paper/partial-label-learning-with-focal-loss-for","slug":"partial-label-learning-with-focal-loss-for","title":"Partial Label Learning with Focal Loss for Sea Ice Classification Based on Ice Charts","date":"2024-06-05","arxiv_id":"2406.03645","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-metadata-assignment-for-cultural","slug":"multimodal-metadata-assignment-for-cultural","title":"Multimodal Metadata Assignment for Cultural Heritage Artifacts","date":"2024-06-01","arxiv_id":"2406.00423","n_code_links":1,"syntology":null},{"paper":null,"slug":"1st-place-solution-to-odyssey-emotion","title":"1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem","date":"2024-05-30","arxiv_id":"2405.20064","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mallows-like-criterion-for-anomaly","title":"A Mallows-like Criterion for Anomaly Detection with Random Forest Implementation","date":"2024-05-29","arxiv_id":"2405.18932","n_code_links":0,"syntology":null},{"paper":null,"slug":"wttfnet-a-weather-time-trajectory-fusion","title":"WTTFNet: A Weather-Time-Trajectory Fusion Network for Pedestrian Trajectory Prediction in Urban Complex","date":"2024-05-29","arxiv_id":"2405.18945","n_code_links":0,"syntology":null},{"paper":null,"slug":"geometric-insights-into-focal-loss-reducing","title":"Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration","date":"2024-05-01","arxiv_id":"2405.00442","n_code_links":0,"syntology":null},{"paper":null,"slug":"fad-sar-a-novel-fishing-activity-detection","title":"FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method","date":"2024-04-28","arxiv_id":"2404.18245","n_code_links":0,"syntology":null},{"paper":null,"slug":"sciflow-empowering-lightweight-optical-flow","title":"SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations","date":"2024-04-11","arxiv_id":"2404.08135","n_code_links":0,"syntology":null},{"paper":"/paper/flightscope-a-deep-comprehensive-assessment","slug":"flightscope-a-deep-comprehensive-assessment","title":"FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery","date":"2024-04-03","arxiv_id":"2404.02877","n_code_links":1,"syntology":null},{"paper":"/paper/emotion-recognition-using-transformers-with","slug":"emotion-recognition-using-transformers-with","title":"Emotion Recognition Using Transformers with Masked Learning","date":"2024-03-19","arxiv_id":"2403.13731","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigation-of-the-impact-of-synthetic","title":"Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection","date":"2024-03-06","arxiv_id":"2403.04809","n_code_links":0,"syntology":null},{"paper":"/paper/multi-level-product-category-prediction","slug":"multi-level-product-category-prediction","title":"Multi-level Product Category Prediction through Text Classification","date":"2024-03-03","arxiv_id":"2403.01638","n_code_links":1,"syntology":null},{"paper":"/paper/iris-sam-iris-segmentation-using-a","slug":"iris-sam-iris-segmentation-using-a","title":"Iris-SAM: Iris Segmentation Using a Foundation Model","date":"2024-02-09","arxiv_id":"2402.06497","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-safety-adapted-loss-for-pedestrian","title":"A Safety-Adapted Loss for Pedestrian Detection in Automated Driving","date":"2024-02-05","arxiv_id":"2402.02986","n_code_links":0,"syntology":null},{"paper":"/paper/plitterstreet-street-level-plastic-litter","slug":"plitterstreet-street-level-plastic-litter","title":"pLitterStreet: Street Level Plastic Litter Detection and Mapping","date":"2024-01-26","arxiv_id":"2401.14719","n_code_links":1,"syntology":null},{"paper":"/paper/vot-revolutionizing-speaker-verification-with","slug":"vot-revolutionizing-speaker-verification-with","title":"A New Perspective on Speaker Verification: Joint Modeling with DFSMN and Transformer","date":"2023-12-28","arxiv_id":"2312.16826","n_code_links":1,"syntology":null},{"paper":null,"slug":"landslide-detection-and-segmentation-using","title":"Landslide Detection and Segmentation Using Remote Sensing Images and Deep Neural Network","date":"2023-12-27","arxiv_id":"2312.16717","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-extended-asymmetric-sigmoid-with","title":"An extended asymmetric sigmoid with Perceptron (SIGTRON) for imbalanced linear classification","date":"2023-12-26","arxiv_id":"2312.16043","n_code_links":0,"syntology":null},{"paper":"/paper/dyra-dynamic-resolution-adjustment-for-scale","slug":"dyra-dynamic-resolution-adjustment-for-scale","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","date":"2023-11-28","arxiv_id":"2311.17098","n_code_links":2,"syntology":null},{"paper":"/paper/multi-channel-cross-modal-detection-of","slug":"multi-channel-cross-modal-detection-of","title":"Multi-Channel Cross Modal Detection of Synthetic Face Images","date":"2023-11-28","arxiv_id":"2311.16773","n_code_links":1,"syntology":null},{"paper":null,"slug":"p2rbox-a-single-point-is-all-you-need-for","title":"P2RBox: Point Prompt Oriented Object Detection with SAM","date":"2023-11-22","arxiv_id":"2311.13128","n_code_links":0,"syntology":null},{"paper":null,"slug":"lidar-based-norwegian-tree-species-detection","title":"Lidar-based Norwegian tree species detection using deep learning","date":"2023-11-10","arxiv_id":"2311.06066","n_code_links":0,"syntology":null},{"paper":"/paper/comparison-of-cross-entropy-dice-and-focal","slug":"comparison-of-cross-entropy-dice-and-focal","title":"Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation","date":"2023-10-26","arxiv_id":"2310.17135","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-segmentation-of-semi-structured-and","title":"Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models","date":"2023-10-26","arxiv_id":"2310.17120","n_code_links":0,"syntology":null},{"paper":null,"slug":"perception-reinforcement-using-auxiliary","title":"Perception Reinforcement Using Auxiliary Learning Feature Fusion: A Modified Yolov8 for Head Detection","date":"2023-10-14","arxiv_id":"2310.09492","n_code_links":0,"syntology":null},{"paper":"/paper/anchor-intermediate-detector-decoupling-and-1","slug":"anchor-intermediate-detector-decoupling-and-1","title":"Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection","date":"2023-10-09","arxiv_id":"2310.05666","n_code_links":1,"syntology":null},{"paper":null,"slug":"danet-enhancing-small-object-detection","title":"DANet: Enhancing Small Object Detection through an Efficient Deformable Attention Network","date":"2023-10-09","arxiv_id":"2310.05768","n_code_links":0,"syntology":null},{"paper":"/paper/robust-gbdt-a-novel-gradient-boosting-model","slug":"robust-gbdt-a-novel-gradient-boosting-model","title":"Robust-GBDT: GBDT with Nonconvex Loss for Tabular Classification in the Presence of Label Noise and Class Imbalance","date":"2023-10-08","arxiv_id":"2310.05067","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-holistic-evaluation-of-piano-sound-quality","title":"A Holistic Evaluation of Piano Sound Quality","date":"2023-10-07","arxiv_id":"2310.04722","n_code_links":0,"syntology":null},{"paper":"/paper/hallucidet-hallucinating-rgb-modality-for","slug":"hallucidet-hallucinating-rgb-modality-for","title":"HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information","date":"2023-10-07","arxiv_id":"2310.04662","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-spatio-temporal-attention-based-method-for","title":"A Spatio-Temporal Attention-Based Method for Detecting Student Classroom Behaviors","date":"2023-10-04","arxiv_id":"2310.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-dentify-deep-learning-for-proximal-caries","title":"AI-Dentify: Deep learning for proximal caries detection on bitewing x-ray -- HUNT4 Oral Health Study","date":"2023-09-30","arxiv_id":"2310.00354","n_code_links":0,"syntology":null},{"paper":"/paper/egocentric-rgb-depth-action-recognition-in","slug":"egocentric-rgb-depth-action-recognition-in","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","date":"2023-09-25","arxiv_id":"2309.13962","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-dice-focal-loss-trained-3d","slug":"generalized-dice-focal-loss-trained-3d","title":"Generalized Dice Focal Loss trained 3D Residual UNet for Automated Lesion Segmentation in Whole-Body FDG PET/CT Images","date":"2023-09-24","arxiv_id":"2309.13553","n_code_links":1,"syntology":null},{"paper":"/paper/unihead-unifying-multi-perception-for","slug":"unihead-unifying-multi-perception-for","title":"UniHead: Unifying Multi-Perception for Detection Heads","date":"2023-09-23","arxiv_id":"2309.13242","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-transformers-for-wireless","slug":"multimodal-transformers-for-wireless","title":"Multimodal Transformers for Wireless Communications: A Case Study in Beam Prediction","date":"2023-09-21","arxiv_id":"2309.11811","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-the-performance-of-r17-type-ii","title":"Improving the Performance of R17 Type-II Codebook with Deep Learning","date":"2023-09-13","arxiv_id":"2310.05962","n_code_links":0,"syntology":null},{"paper":null,"slug":"dmkd-improving-feature-based-knowledge","title":"DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation","date":"2023-09-06","arxiv_id":"2309.02719","n_code_links":0,"syntology":null},{"paper":null,"slug":"focaldreamer-text-driven-3d-editing-via-focal","title":"FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly","date":"2023-08-21","arxiv_id":"2308.10608","n_code_links":0,"syntology":null},{"paper":null,"slug":"kesdt-knowledge-enhanced-shallow-and-deep","title":"KESDT: knowledge enhanced shallow and deep Transformer for detecting adverse drug reactions","date":"2023-08-18","arxiv_id":"2308.09329","n_code_links":0,"syntology":null},{"paper":"/paper/online-class-incremental-learning-on","slug":"online-class-incremental-learning-on","title":"Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning","date":"2023-08-18","arxiv_id":"2308.09303","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-lightweight-object-detectors-via","title":"Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation","date":"2023-08-17","arxiv_id":"2308.09105","n_code_links":0,"syntology":null},{"paper":"/paper/ensemble-modeling-for-multimodal-visual","slug":"ensemble-modeling-for-multimodal-visual","title":"Ensemble Modeling for Multimodal Visual Action Recognition","date":"2023-08-10","arxiv_id":"2308.05430","n_code_links":1,"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/eflnet-enhancing-feature-learning-for","slug":"eflnet-enhancing-feature-learning-for","title":"EFLNet: Enhancing Feature Learning for Infrared Small Target Detection","date":"2023-07-27","arxiv_id":"2307.14723","n_code_links":1,"syntology":null},{"paper":"/paper/aligndet-aligning-pre-training-and-fine","slug":"aligndet-aligning-pre-training-and-fine","title":"AlignDet: Aligning Pre-training and Fine-tuning in Object Detection","date":"2023-07-20","arxiv_id":"2307.11077","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["liming-ai/AlignDet"],"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":"intelligent-model-for-offshore-china-sea-fog","title":"Intelligent model for offshore China sea fog forecasting","date":"2023-07-20","arxiv_id":"2307.10580","n_code_links":0,"syntology":null},{"paper":null,"slug":"vertex-based-networks-to-accelerate-path","title":"Vertex-based Networks to Accelerate Path Planning Algorithms","date":"2023-07-13","arxiv_id":"2307.07059","n_code_links":0,"syntology":null},{"paper":"/paper/compact-twice-fusion-network-for-edge","slug":"compact-twice-fusion-network-for-edge","title":"Compact Twice Fusion Network for Edge Detection","date":"2023-07-11","arxiv_id":"2307.04952","n_code_links":1,"syntology":null},{"paper":null,"slug":"hate-speech-detection-via-dual-contrastive","title":"Hate Speech Detection via Dual Contrastive Learning","date":"2023-07-10","arxiv_id":"2307.05578","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":461,"with_a_code_link":236,"where_syntology_ran_a_sample":52,"not_listed_spam_title":0,"listed":461,"listed_where_code_ran":52,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":42,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":42,"listed_every_run_a_failure_of_syntologys_instrument":10,"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":52,"papers_where_code_ran_first_page":"/method/focal-loss/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":5,"url":"/method/focal-loss/papers/2","json":"/method/focal-loss/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/method/focal-loss/papers/3","json":"/method/focal-loss/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/method/focal-loss/papers/4","json":"/method/focal-loss/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/method/focal-loss/papers/5","json":"/method/focal-loss/papers/5.json","rows":61},{"order":"ran","page":1,"of":1,"url":"/method/focal-loss/papers/ran/1","json":"/method/focal-loss/papers/ran/1.json","rows":52}],"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":202},{"task":"/task/object-detection-1","name":"object-detection","papers":186},{"task":"/task/object","name":"Object","papers":121},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":46},{"task":"/task/image-classification","name":"Image Classification","papers":33},{"task":"/task/segmentation","name":"Segmentation","papers":33},{"task":"/task/classification","name":"General Classification","papers":25},{"task":"/task/image-classification","name":"image-classification","papers":25},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":23},{"task":"/task/classification-1","name":"Classification","papers":21},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":21},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":20},{"task":"/task/deep-learning","name":"Deep Learning","papers":19},{"task":"/task/decoder","name":"Decoder","papers":18},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":16},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":16},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":13},{"task":"/task/pedestrian-detection","name":"Pedestrian Detection","papers":13},{"task":"/task/regression-1","name":"regression","papers":12},{"task":null,"name":"GPU","papers":11}],"tasks_shown":20,"n_tasks":341,"usage_by_year":[{"year":"2017","papers":5},{"year":"2018","papers":26},{"year":"2019","papers":68},{"year":"2020","papers":66},{"year":"2021","papers":80},{"year":"2022","papers":67},{"year":"2023","papers":84},{"year":"2024","papers":48},{"year":"2025","papers":17}],"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/focal-loss"},"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=Focal%20Loss","read_at":"2026-10-05T00:56:06+00:00","query":"Focal Loss","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"FOCAL","origin_arxiv_id":"2507.10375"},"resolution":"token_match","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"1708.02002","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2507.10375","citations":5},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Focal Loss'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2507.10375","page":"/paper/test-time-canonicalization-by-foundation","syntology_url":"https://syntology.ai/paper/2507.10375","in_graph_layer":true,"samples":5,"ran":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"for a different name, 'FOCAL', about another paper, arXiv:2507.10375: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'FOCAL' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2507.10375, while the archive credits arXiv:1708.02002.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"3abd93a105c9280d6bd7a88e9f920e47be643a35dd109efac927b4e4069a2004","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}