{"url":"/task/self-knowledge-distillation","name":"Self-Knowledge Distillation","slug":"self-knowledge-distillation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":68,"papers_with_code":36,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/knowledge-distillation","name":"Knowledge Distillation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":36,"tagged_in_all":68,"items":[{"url":"/paper/proselflc-progressive-self-label-correction","title":"ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks","date":"2020-05-07","arxiv_id":"2005.03788","repositories_listed":5,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/bge-m3-embedding-multi-lingual-multi","title":"BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","date":"2024-02-05","arxiv_id":"2402.03216","repositories_listed":4,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/preservation-of-the-global-knowledge-by-not","title":"Preservation of the Global Knowledge by Not-True Distillation in Federated Learning","date":"2021-06-06","arxiv_id":"2106.03097","repositories_listed":3,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/fedsol-bridging-global-alignment-and-local","title":"FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning","date":"2023-08-24","arxiv_id":"2308.12532","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/revisit-knowledge-distillation-a-teacher-free","title":"Revisiting Knowledge Distillation via Label Smoothing Regularization","date":"2019-09-25","arxiv_id":"1909.11723","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/tackling-data-heterogeneity-in-federated-2","title":"Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation","date":"2025-06-25","arxiv_id":"2506.20431","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-lung-ultrasound-severity-scoring","title":"Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature Extractor","date":"2025-01-21","arxiv_id":"2501.12524","repositories_listed":1,"syntology":null},{"url":"/paper/frequency-guided-masking-for-enhanced-vision","title":"Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning","date":"2024-09-16","arxiv_id":"2409.10362","repositories_listed":1,"syntology":null},{"url":"/paper/salnas-efficient-saliency-prediction-neural","title":"SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation","date":"2024-07-29","arxiv_id":"2407.20062","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-generalizable-pathology-foundation","title":"Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation","date":"2024-07-26","arxiv_id":"2407.18449","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/skd-tstsan-three-stream-temporal-shift","title":"Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition","date":"2024-06-25","arxiv_id":"2406.17538","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-frame-level-ctc-alignments-using-self","title":"Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation","date":"2024-06-12","arxiv_id":"2406.07909","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-meets-the-skeleton","title":"Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning","date":"2024-05-31","arxiv_id":"2405.20606","repositories_listed":1,"syntology":null},{"url":"/paper/crossmatch-enhance-semi-supervised-medical","title":"CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge Distillation","date":"2024-05-01","arxiv_id":"2405.00354","repositories_listed":1,"syntology":null},{"url":"/paper/distilled-gradual-pruning-with-pruned-fine","title":"Distilled Gradual Pruning with Pruned Fine-tuning","date":"2024-02-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-clustering-with-diffused-sampling-and","title":"Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation","date":"2024-01-25","arxiv_id":"2401.14038","repositories_listed":1,"syntology":null},{"url":"/paper/combining-inherent-knowledge-of-vision","title":"Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance","date":"2023-12-07","arxiv_id":"2312.04066","repositories_listed":1,"syntology":null},{"url":"/paper/promoting-generalized-cross-lingual-question","title":"Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation","date":"2023-09-29","arxiv_id":"2309.17134","repositories_listed":1,"syntology":null},{"url":"/paper/eyelids-intrinsic-motion-aware-feature","title":"Eyelid’s Intrinsic Motion-aware Feature Learning for Real-time Eyeblink Detection in the Wild","date":"2023-08-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/effective-whole-body-pose-estimation-with-two","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","date":"2023-07-29","arxiv_id":"2307.15880","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/robust-spatiotemporal-traffic-forecasting","title":"Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training","date":"2023-06-25","arxiv_id":"2306.14126","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-graph-information-in","title":"Incorporating Graph Information in Transformer-based AMR Parsing","date":"2023-06-23","arxiv_id":"2306.13467","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-self-knowledge-distillation-with","title":"Lightweight Self-Knowledge Distillation with Multi-source Information Fusion","date":"2023-05-16","arxiv_id":"2305.09183","repositories_listed":1,"syntology":null},{"url":"/paper/from-knowledge-distillation-to-self-knowledge","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","date":"2023-03-23","arxiv_id":"2303.13005","repositories_listed":1,"syntology":null},{"url":"/paper/dualfair-fair-representation-learning-at-both","title":"DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision","date":"2023-03-15","arxiv_id":"2303.08403","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/graph-based-knowledge-distillation-a-survey","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","date":"2023-02-27","arxiv_id":"2302.14643","repositories_listed":1,"syntology":null},{"url":"/paper/multimodality-multi-lead-ecg-arrhythmia","title":"Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning","date":"2022-09-30","arxiv_id":"2210.06297","repositories_listed":1,"syntology":null},{"url":"/paper/toward-better-target-representation-for","title":"RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation","date":"2022-08-22","arxiv_id":"2208.10531","repositories_listed":1,"syntology":null},{"url":"/paper/mixskd-self-knowledge-distillation-from-mixup","title":"MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition","date":"2022-08-11","arxiv_id":"2208.05768","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/sequential-recommendation-with-bidirectional","title":"Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training","date":"2021-12-13","arxiv_id":"2112.06460","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}