{"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/knowledge-distillation/papers/28","list_of":"/method/knowledge-distillation","method":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":28,"pages_in_order":31,"rows_per_page":100,"rows":[2701,2800],"of":3071,"counts":{"archive_papers_tagged":3071,"with_a_code_link":1258,"where_syntology_ran_a_sample":320,"not_listed_spam_title":0,"listed":3071,"listed_where_code_ran":320,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":276,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":276,"listed_every_run_a_failure_of_syntologys_instrument":44,"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"},"first_page":"/method/knowledge-distillation","prev":"/method/knowledge-distillation/papers/27","next":"/method/knowledge-distillation/papers/29","papers":[{"paper":"/paper/spherical-knowledge-distillation","slug":"spherical-knowledge-distillation","title":"Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation","date":"2020-10-15","arxiv_id":"2010.07485","n_code_links":1,"syntology":null},{"paper":null,"slug":"autoadr-automatic-model-design-for-ad","title":"AutoADR: Automatic Model Design for Ad Relevance","date":"2020-10-14","arxiv_id":"2010.07075","n_code_links":0,"syntology":null},{"paper":null,"slug":"mulde-multi-teacher-knowledge-distillation","title":"MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings","date":"2020-10-14","arxiv_id":"2010.07152","n_code_links":0,"syntology":null},{"paper":"/paper/task-decoupled-knowledge-distillation-for","slug":"task-decoupled-knowledge-distillation-for","title":"Task Decoupled Knowledge Distillation For Lightweight Face Detectors","date":"2020-10-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"collective-wisdom-improving-low-resource","title":"Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation","date":"2020-10-12","arxiv_id":"2010.05445","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-asr-unify-and-improve-streaming-asr-1","title":"Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling","date":"2020-10-12","arxiv_id":"2010.06030","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-a-deep-neural-network-into-a","title":"Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System","date":"2020-10-10","arxiv_id":"2010.04974","n_code_links":0,"syntology":null},{"paper":"/paper/structural-knowledge-distillation-1","slug":"structural-knowledge-distillation-1","title":"Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor","date":"2020-10-10","arxiv_id":"2010.05010","n_code_links":1,"syntology":null},{"paper":null,"slug":"be-your-own-best-competitor-multi-branched","title":"Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer","date":"2020-10-09","arxiv_id":"2010.04516","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-region-knowledge-distillation","title":"Locally Linear Region Knowledge Distillation","date":"2020-10-09","arxiv_id":"2010.04812","n_code_links":0,"syntology":null},{"paper":null,"slug":"dipair-fast-and-accurate-distillation-for","title":"DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling","date":"2020-10-07","arxiv_id":"2010.03099","n_code_links":0,"syntology":null},{"paper":null,"slug":"galileo-at-semeval-2020-task-12-multi-lingual","title":"Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models","date":"2020-10-07","arxiv_id":"2010.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-representation-learning-of-patient-data","title":"Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review","date":"2020-10-06","arxiv_id":"2010.02809","n_code_links":0,"syntology":null},{"paper":"/paper/improving-efficient-neural-ranking-models","slug":"improving-efficient-neural-ranking-models","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","date":"2020-10-06","arxiv_id":"2010.02666","n_code_links":1,"syntology":null},{"paper":"/paper/why-skip-if-you-can-combine-a-simple","slug":"why-skip-if-you-can-combine-a-simple","title":"Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers","date":"2020-10-06","arxiv_id":"2010.03034","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["yimeng0701/CKD_pytorch"],"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/improving-neural-topic-models-using-knowledge","slug":"improving-neural-topic-models-using-knowledge","title":"Improving Neural Topic Models using Knowledge Distillation","date":"2020-10-05","arxiv_id":"2010.02377","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["ahoho/kd-topic-models"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/lifelong-language-knowledge-distillation","slug":"lifelong-language-knowledge-distillation","title":"Lifelong Language Knowledge Distillation","date":"2020-10-05","arxiv_id":"2010.02123","n_code_links":1,"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":["voidism/L2KD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-cross-modality-medical-image","title":"Towards Cross-modality Medical Image Segmentation with Online Mutual Knowledge Distillation","date":"2020-10-04","arxiv_id":"2010.01532","n_code_links":0,"syntology":null},{"paper":null,"slug":"neighbourhood-distillation-on-the-benefits-of-1","title":"Neighbourhood Distillation: On the benefits of non end-to-end distillation","date":"2020-10-02","arxiv_id":"2010.01189","n_code_links":0,"syntology":null},{"paper":null,"slug":"online-knowledge-distillation-via-multi","title":"Online Knowledge Distillation via Multi-branch Diversity Enhancement","date":"2020-10-02","arxiv_id":"2010.00795","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-kernel-transfer-in-knowledge","slug":"efficient-kernel-transfer-in-knowledge","title":"Improved Knowledge Distillation via Full Kernel Matrix Transfer","date":"2020-09-30","arxiv_id":"2009.14416","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idstcv/kda"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pea-kd-parameter-efficient-and-accurate","title":"Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT","date":"2020-09-30","arxiv_id":"2009.14822","n_code_links":0,"syntology":null},{"paper":null,"slug":"stochastic-precision-ensemble-self-knowledge","title":"Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks","date":"2020-09-30","arxiv_id":"2009.14502","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-distillation-on-intermediate","slug":"contrastive-distillation-on-intermediate","title":"Contrastive Distillation on Intermediate Representations for Language Model Compression","date":"2020-09-29","arxiv_id":"2009.14167","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["intersun/CoDIR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tinygan-distilling-biggan-for-conditional","slug":"tinygan-distilling-biggan-for-conditional","title":"TinyGAN: Distilling BigGAN for Conditional Image Generation","date":"2020-09-29","arxiv_id":"2009.13829","n_code_links":1,"syntology":null},{"paper":null,"slug":"kernel-based-progressive-distillation-for","title":"Kernel Based Progressive Distillation for Adder Neural Networks","date":"2020-09-28","arxiv_id":"2009.13044","n_code_links":0,"syntology":null},{"paper":null,"slug":"pea-kd-parameter-efficient-and-accurate-1","title":"Pea-KD: Parameter-efficient and accurate Knowledge Distillation","date":"2020-09-28","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ternarybert-distillation-aware-ultra-low-bit","slug":"ternarybert-distillation-aware-ultra-low-bit","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","date":"2020-09-27","arxiv_id":"2009.12812","n_code_links":5,"syntology":null},{"paper":null,"slug":"multi-frame-to-single-frame-knowledge","title":"Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection","date":"2020-09-24","arxiv_id":"2009.11859","n_code_links":0,"syntology":null},{"paper":"/paper/n-ltp-a-open-source-neural-chinese-language","slug":"n-ltp-a-open-source-neural-chinese-language","title":"N-LTP: An Open-source Neural Language Technology Platform for Chinese","date":"2020-09-24","arxiv_id":"2009.11616","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-set-short-utterance-forensic-speaker","title":"Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias","date":"2020-09-21","arxiv_id":"2009.09556","n_code_links":0,"syntology":null},{"paper":null,"slug":"ei-mtd-moving-target-defense-for-edge","title":"EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks","date":"2020-09-19","arxiv_id":"2009.10537","n_code_links":0,"syntology":null},{"paper":null,"slug":"weight-distillation-transferring-the","title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","date":"2020-09-19","arxiv_id":"2009.09152","n_code_links":0,"syntology":null},{"paper":"/paper/densely-guided-knowledge-distillation-using","slug":"densely-guided-knowledge-distillation-using","title":"Densely Guided Knowledge Distillation using Multiple Teacher Assistants","date":"2020-09-18","arxiv_id":"2009.08825","n_code_links":1,"syntology":null},{"paper":"/paper/meal-v2-boosting-vanilla-resnet-50-to-80-top","slug":"meal-v2-boosting-vanilla-resnet-50-to-80-top","title":"MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks","date":"2020-09-17","arxiv_id":"2009.08453","n_code_links":1,"syntology":null},{"paper":"/paper/s2sd-simultaneous-similarity-based-self","slug":"s2sd-simultaneous-similarity-based-self","title":"S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning","date":"2020-09-17","arxiv_id":"2009.08348","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":["MLforHealth/S2SD"],"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":null,"slug":"mimic-and-conquer-heterogeneous-tree","title":"Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP","date":"2020-09-16","arxiv_id":"2009.07411","n_code_links":0,"syntology":null},{"paper":"/paper/simplified-tinybert-knowledge-distillation","slug":"simplified-tinybert-knowledge-distillation","title":"Simplified TinyBERT: Knowledge Distillation for Document Retrieval","date":"2020-09-16","arxiv_id":"2009.07531","n_code_links":4,"syntology":null},{"paper":null,"slug":"collaborative-distillation-in-the-parameter","title":"Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition","date":"2020-09-15","arxiv_id":"2009.06902","n_code_links":0,"syntology":null},{"paper":null,"slug":"boostingbert-integrating-multi-class-boosting","title":"BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks","date":"2020-09-13","arxiv_id":"2009.05959","n_code_links":0,"syntology":null},{"paper":null,"slug":"distile-distiling-knowledge-graph-embeddings","title":"DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning","date":"2020-09-13","arxiv_id":"2009.05912","n_code_links":0,"syntology":null},{"paper":null,"slug":"sskd-self-supervised-knowledge-distillation","title":"SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification","date":"2020-09-13","arxiv_id":"2009.05972","n_code_links":0,"syntology":null},{"paper":null,"slug":"extending-label-smoothing-regularization-with","title":"Extending Label Smoothing Regularization with Self-Knowledge Distillation","date":"2020-09-11","arxiv_id":"2009.05226","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-orthogonality-of-knowledge","title":"On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective","date":"2020-09-09","arxiv_id":"2009.04120","n_code_links":0,"syntology":null},{"paper":null,"slug":"lifelong-object-detection","title":"Lifelong Object Detection","date":"2020-09-02","arxiv_id":"2009.01129","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-assignment-of-radiology-examination","slug":"automatic-assignment-of-radiology-examination","title":"Automatic Assignment of Radiology Examination Protocols Using Pre-trained Language Models with Knowledge Distillation","date":"2020-09-01","arxiv_id":"2009.00694","n_code_links":1,"syntology":null},{"paper":null,"slug":"classification-of-diabetic-retinopathy-using","title":"Classification of Diabetic Retinopathy Using Unlabeled Data and Knowledge Distillation","date":"2020-09-01","arxiv_id":"2009.00982","n_code_links":0,"syntology":null},{"paper":"/paper/semantics-aware-adaptive-knowledge","slug":"semantics-aware-adaptive-knowledge","title":"Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition","date":"2020-09-01","arxiv_id":"2009.00210","n_code_links":1,"syntology":null},{"paper":"/paper/initial-classifier-weights-replay-for","slug":"initial-classifier-weights-replay-for","title":"Initial Classifier Weights Replay for Memoryless Class Incremental Learning","date":"2020-08-31","arxiv_id":"2008.13710","n_code_links":1,"syntology":null},{"paper":"/paper/performance-optimization-for-federated-person","slug":"performance-optimization-for-federated-person","title":"Performance Optimization for Federated Person Re-identification via Benchmark Analysis","date":"2020-08-26","arxiv_id":"2008.11560","n_code_links":2,"syntology":null},{"paper":"/paper/active-class-incremental-learning-for","slug":"active-class-incremental-learning-for","title":"Active Class Incremental Learning for Imbalanced Datasets","date":"2020-08-25","arxiv_id":"2008.10968","n_code_links":1,"syntology":null},{"paper":null,"slug":"learn-to-talk-via-proactive-knowledge","title":"Learn to Talk via Proactive Knowledge Transfer","date":"2020-08-23","arxiv_id":"2008.10077","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-person-full-body-pose-estimation","title":"Multi-Person Full Body Pose Estimation","date":"2020-08-23","arxiv_id":"2008.10060","n_code_links":0,"syntology":null},{"paper":null,"slug":"rectified-decision-trees-exploring-the","title":"Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning","date":"2020-08-21","arxiv_id":"2008.09413","n_code_links":0,"syntology":null},{"paper":null,"slug":"cascaded-channel-pruning-using-hierarchical","title":"Cascaded channel pruning using hierarchical self-distillation","date":"2020-08-16","arxiv_id":"2008.06814","n_code_links":0,"syntology":null},{"paper":null,"slug":"compression-of-deep-learning-models-for-text","title":"Compression of Deep Learning Models for Text: A Survey","date":"2020-08-12","arxiv_id":"2008.05221","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-unsupervised-crowd-counting-via","title":"Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer","date":"2020-08-12","arxiv_id":"2008.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"compact-speaker-embedding-lrx-vector","title":"Compact Speaker Embedding: lrx-vector","date":"2020-08-11","arxiv_id":"2008.05011","n_code_links":0,"syntology":null},{"paper":null,"slug":"s2osc-a-holistic-semi-supervised-approach-for","title":"S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification","date":"2020-08-11","arxiv_id":"2008.04662","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-the-knowledge-of-bert-for-sequence","slug":"distilling-the-knowledge-of-bert-for-sequence","title":"Distilling the Knowledge of BERT for Sequence-to-Sequence ASR","date":"2020-08-09","arxiv_id":"2008.03822","n_code_links":1,"syntology":null},{"paper":null,"slug":"lrspeech-extremely-low-resource-speech","title":"LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition","date":"2020-08-09","arxiv_id":"2008.03687","n_code_links":0,"syntology":null},{"paper":null,"slug":"med-tex-transferring-and-explaining-knowledge","title":"MED-TEX: Transferring and Explaining Knowledge with Less Data from Pretrained Medical Imaging Models","date":"2020-08-06","arxiv_id":"2008.02593","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacher-student-training-and-triplet-loss-for","title":"Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion","date":"2020-08-03","arxiv_id":"2008.01003","n_code_links":0,"syntology":null},{"paper":null,"slug":"tutornet-towards-flexible-knowledge","title":"TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition","date":"2020-08-03","arxiv_id":"2008.00671","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentiable-feature-aggregation-search-for","title":"Differentiable Feature Aggregation Search for Knowledge Distillation","date":"2020-08-02","arxiv_id":"2008.00506","n_code_links":0,"syntology":null},{"paper":null,"slug":"amln-adversarial-based-mutual-learning","title":"AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation","date":"2020-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/distilling-visual-priors-from-self-supervised","slug":"distilling-visual-priors-from-self-supervised","title":"Distilling Visual Priors from Self-Supervised Learning","date":"2020-08-01","arxiv_id":"2008.00261","n_code_links":1,"syntology":null},{"paper":"/paper/feature-normalized-knowledge-distillation-for","slug":"feature-normalized-knowledge-distillation-for","title":"Feature Normalized Knowledge Distillation for Image Classification","date":"2020-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/improving-knowledge-distillation-via-category","slug":"improving-knowledge-distillation-via-category","title":"Improving Knowledge Distillation via Category Structure","date":"2020-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/intra-class-feature-variation-distillation","slug":"intra-class-feature-variation-distillation","title":"Intra-class Feature Variation Distillation for Semantic Segmentation","date":"2020-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"local-correlation-consistency-for-knowledge","title":"Local Correlation Consistency for Knowledge Distillation","date":"2020-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"weight-decay-scheduling-and-knowledge","title":"Weight Decay Scheduling and Knowledge Distillation for Active Learning","date":"2020-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"yolo-in-the-dark-domain-adaptation-method-for","title":"YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -","date":"2020-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/neural-compression-and-filtering-for-edge","slug":"neural-compression-and-filtering-for-edge","title":"Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks","date":"2020-07-31","arxiv_id":"2007.15818","n_code_links":2,"syntology":null},{"paper":"/paper/group-knowledge-transfer-collaborative","slug":"group-knowledge-transfer-collaborative","title":"Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge","date":"2020-07-28","arxiv_id":"2007.14513","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["FedML-AI/FedML"],"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/weakly-supervised-3d-object-detection-from-1","slug":"weakly-supervised-3d-object-detection-from-1","title":"Weakly Supervised 3D Object Detection from Point Clouds","date":"2020-07-28","arxiv_id":"2007.13970","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["Zengyi-Qin/Weakly-Supervised-3D-Object-Detection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/split-computing-for-complex-object-detectors","slug":"split-computing-for-complex-object-detectors","title":"Split Computing for Complex Object Detectors: Challenges and Preliminary Results","date":"2020-07-27","arxiv_id":"2007.13312","n_code_links":2,"syntology":null},{"paper":null,"slug":"dynamic-knowledge-distillation-for-black-box","title":"Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning","date":"2020-07-24","arxiv_id":"2007.12355","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-foreground-object-search-as","title":"Interpretable Foreground Object Search As Knowledge Distillation","date":"2020-07-20","arxiv_id":"2007.09867","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-label-contrastive-predictive-coding","title":"Multi-label Contrastive Predictive Coding","date":"2020-07-20","arxiv_id":"2007.09852","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-in-deep-learning-and","title":"Knowledge Distillation in Deep Learning and its Applications","date":"2020-07-17","arxiv_id":"2007.09029","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervision-on-unlabelled-or-data-for","slug":"self-supervision-on-unlabelled-or-data-for","title":"Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose Estimation","date":"2020-07-16","arxiv_id":"2007.08354","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-for-multi-task","slug":"knowledge-distillation-for-multi-task","title":"Knowledge Distillation for Multi-task Learning","date":"2020-07-14","arxiv_id":"2007.06889","n_code_links":4,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":4,"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":["VICO-UoE/KD4MTL"],"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/p-kdgan-progressive-knowledge-distillation","slug":"p-kdgan-progressive-knowledge-distillation","title":"P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection","date":"2020-07-14","arxiv_id":"2007.06963","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-multi-target-domain-adaptation-2","slug":"unsupervised-multi-target-domain-adaptation-2","title":"Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation","date":"2020-07-14","arxiv_id":"2007.07077","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-learn-parameterized","slug":"learning-to-learn-parameterized","title":"Learning to Learn Parameterized Classification Networks for Scalable Input Images","date":"2020-07-13","arxiv_id":"2007.06181","n_code_links":1,"syntology":null},{"paper":"/paper/ratt-recurrent-attention-to-transient-tasks","slug":"ratt-recurrent-attention-to-transient-tasks","title":"RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning","date":"2020-07-13","arxiv_id":"2007.06271","n_code_links":2,"syntology":null},{"paper":"/paper/temporal-self-ensembling-teacher-for-semi","slug":"temporal-self-ensembling-teacher-for-semi","title":"Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection","date":"2020-07-13","arxiv_id":"2007.06144","n_code_links":1,"syntology":null},{"paper":"/paper/towards-practical-lipreading-with-distilled","slug":"towards-practical-lipreading-with-distilled","title":"Towards Practical Lipreading with Distilled and Efficient Models","date":"2020-07-13","arxiv_id":"2007.06504","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-efficient-ranking-distillation-for-image","title":"Data-Efficient Ranking Distillation for Image Retrieval","date":"2020-07-10","arxiv_id":"2007.05299","n_code_links":0,"syntology":null},{"paper":null,"slug":"optical-flow-distillation-towards-efficient","title":"Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer","date":"2020-07-10","arxiv_id":"2007.05146","n_code_links":0,"syntology":null},{"paper":"/paper/a-distilled-model-for-tracking-and-tracker","slug":"a-distilled-model-for-tracking-and-tracker","title":"Tracking-by-Trackers with a Distilled and Reinforced Model","date":"2020-07-08","arxiv_id":"2007.04108","n_code_links":1,"syntology":null},{"paper":"/paper/robust-re-identification-by-multiple-views","slug":"robust-re-identification-by-multiple-views","title":"Robust Re-Identification by Multiple Views Knowledge Distillation","date":"2020-07-08","arxiv_id":"2007.04174","n_code_links":1,"syntology":null},{"paper":null,"slug":"interactive-knowledge-distillation","title":"Interactive Knowledge Distillation","date":"2020-07-03","arxiv_id":"2007.01476","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-beyond-model","title":"Knowledge Distillation Beyond Model Compression","date":"2020-07-03","arxiv_id":"2007.01922","n_code_links":0,"syntology":null},{"paper":null,"slug":"casia-s-system-for-iwslt-2020-open-domain","title":"CASIA's System for IWSLT 2020 Open Domain Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-simple-learners-in","title":"Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-event-detection-via-open-domain","slug":"improving-event-detection-via-open-domain","title":"Improving Event Detection via Open-domain Trigger Knowledge","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"simulspeech-end-to-end-simultaneous-speech-to","title":"SimulSpeech: End-to-End Simultaneous Speech to Text Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extracurricular-learning-knowledge-transfer","title":"Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution","date":"2020-06-30","arxiv_id":"2007.00051","n_code_links":0,"syntology":null}],"record_sha256":"e0bf4381ccd0fbc30301bbd4c3db4d844e9bba8d70edd1e92e08ec2e8b8f739d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}