{"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":"/task/knowledge-distillation/papers/40","list_of":"/task/knowledge-distillation","task":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":40,"pages_in_order":43,"rows_per_page":100,"rows":[3901,4000],"of":4240,"counts":{"archive_papers_tagged":4240,"with_a_code_link":1740,"where_syntology_ran_a_sample":451,"not_listed_spam_title":0,"listed":4240,"listed_where_code_ran":451,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":380,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":380,"listed_every_run_a_failure_of_syntologys_instrument":71,"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":"/task/knowledge-distillation","prev":"/task/knowledge-distillation/papers/39","next":"/task/knowledge-distillation/papers/41","papers":[{"url":null,"slug":"distilling-structured-knowledge-for-text","title":"Distilling Structured Knowledge for Text-Based Relational Reasoning","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-end-to-end-coreference-resolution-for","title":"Fast End-to-end Coreference Resolution for Korean","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feded-federated-learning-via-ensemble","title":"FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"high-performance-natural-language-processing","title":"High Performance Natural Language Processing","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hw-tscs-participation-in-the-wmt-2020-news","title":"HW-TSC’s Participation in the WMT 2020 News Translation Shared Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iies-neural-machine-translation-systems-for","title":"IIE’s Neural Machine Translation Systems for WMT20","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mixkd-towards-efficient-distillation-of-large-1","title":"MixKD: Towards Efficient Distillation of Large-scale Language Models","date":"2020-11-01","arxiv_id":"2011.00593","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-niutrans-machine-translation-systems-for-2","title":"The NiuTrans Machine Translation Systems for WMT20","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-the-past-knowledge-to-improve-sentiment","title":"Using the Past Knowledge to Improve Sentiment Classification","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"proxylesskd-direct-knowledge-distillation-1","title":"ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition","date":"2020-10-31","arxiv_id":"2011.00265","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-machine-reading-comprehension-1","title":"Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation","date":"2020-10-27","arxiv_id":"2010.14271","repositories_listed":0,"syntology":null},{"url":null,"slug":"activation-map-adaptation-for-effective","title":"Activation Map Adaptation for Effective Knowledge Distillation","date":"2020-10-26","arxiv_id":"2010.13500","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-knowledge-distillation-via-open","title":"Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification","date":"2020-10-25","arxiv_id":"2010.13114","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-synthetic-training-for-reading","title":"Improved Synthetic Training for Reading Comprehension","date":"2020-10-24","arxiv_id":"2010.12776","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-long-financial-report-using","title":"Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation","date":"2020-10-23","arxiv_id":"2010.12188","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-graph-self-distillation-1","title":"Iterative Graph Self-Distillation","date":"2020-10-23","arxiv_id":"2010.12609","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-attention-based-knowledge","title":"Contextualized Attention-based Knowledge Transfer for Spoken Conversational Question Answering","date":"2020-10-21","arxiv_id":"2010.11066","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-improved-accuracy","title":"Knowledge Distillation for Improved Accuracy in Spoken Question Answering","date":"2020-10-21","arxiv_id":"2010.11067","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-edge-learning-using-cloned-1","title":"Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation","date":"2020-10-20","arxiv_id":"2010.10338","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-video-salient-object-detection-via","title":"Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation","date":"2020-10-20","arxiv_id":"2010.10027","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-wide-neural","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","date":"2020-10-20","arxiv_id":"2010.10090","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-fisher-information-regularization","title":"Comparing Fisher Information Regularization with Distillation for DNN Quantization","date":"2020-10-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-neural-network-compression-for-analog","title":"Noisy Neural Network Compression for Analog Storage Devices","date":"2020-10-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"autoadr-automatic-model-design-for-ad","title":"AutoADR: Automatic Model Design for Ad Relevance","date":"2020-10-14","arxiv_id":"2010.07075","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-self-supervised-data-free","title":"Adversarial Self-Supervised Data-Free Distillation for Text Classification","date":"2020-10-10","arxiv_id":"2010.04883","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-region-knowledge-distillation","title":"Locally Linear Region Knowledge Distillation","date":"2020-10-09","arxiv_id":"2010.04812","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-neural-network-compression","title":"A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions","date":"2020-10-05","arxiv_id":"2010.03954","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-knowledge-distillation-via-multi","title":"Online Knowledge Distillation via Multi-branch Diversity Enhancement","date":"2020-10-02","arxiv_id":"2010.00795","repositories_listed":0,"syntology":null},{"url":null,"slug":"wechat-neural-machine-translation-systems-for","title":"WeChat Neural Machine Translation Systems for WMT20","date":"2020-10-01","arxiv_id":"2010.00247","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillation-of-weighted-automata-from","title":"Distillation of Weighted Automata from Recurrent Neural Networks using a Spectral Approach","date":"2020-09-28","arxiv_id":"2009.13101","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-based-progressive-distillation-for","title":"Kernel Based Progressive Distillation for Adder Neural Networks","date":"2020-09-28","arxiv_id":"2009.13044","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-transfer-in-deep-reinforcement","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","date":"2020-09-24","arxiv_id":"2009.13303","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"introspective-learning-by-distilling","title":"Introspective Learning by Distilling Knowledge from Online Self-explanation","date":"2020-09-19","arxiv_id":"2009.09140","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-distillation-transferring-the","title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","date":"2020-09-19","arxiv_id":"2009.09152","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-based-large-scale","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","date":"2020-09-17","arxiv_id":"2009.08065","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-label-smoothing-regularization-with","title":"Extending Label Smoothing Regularization with Self-Knowledge Distillation","date":"2020-09-11","arxiv_id":"2009.05226","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-object-detection","title":"Lifelong Object Detection","date":"2020-09-02","arxiv_id":"2009.01129","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-smoothing-graph-neural","title":"SAIL: Self-Augmented Graph Contrastive Learning","date":"2020-09-02","arxiv_id":"2009.00934","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"metadistiller-network-self-boosting-via-meta","title":"MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation","date":"2020-08-27","arxiv_id":"2008.12094","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-adversarial-self-mining-a-simple-method","title":"Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition","date":"2020-08-26","arxiv_id":"2008.11401","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-talk-via-proactive-knowledge","title":"Learn to Talk via Proactive Knowledge Transfer","date":"2020-08-23","arxiv_id":"2008.10077","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-person-full-body-pose-estimation","title":"Multi-Person Full Body Pose Estimation","date":"2020-08-23","arxiv_id":"2008.10060","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-extract-attribute-value-from","title":"Learning to Extract Attribute Value from Product via Question Answering: A Multi-task Approach","date":"2020-08-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-channel-pruning-using-hierarchical","title":"Cascaded channel pruning using hierarchical self-distillation","date":"2020-08-16","arxiv_id":"2008.06814","repositories_listed":0,"syntology":null},{"url":"/paper/an-ensemble-of-knowledge-sharing-models-for","slug":"an-ensemble-of-knowledge-sharing-models-for","title":"An Ensemble of Knowledge Sharing Models for Dynamic Hand Gesture Recognition","date":"2020-08-13","arxiv_id":"2008.05732","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"compact-speaker-embedding-lrx-vector","title":"Compact Speaker Embedding: lrx-vector","date":"2020-08-11","arxiv_id":"2008.05011","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-precoding-in-multiuser","title":"Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback","date":"2020-08-10","arxiv_id":"2008.04147","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-and-data-selection-for","title":"Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models","date":"2020-08-10","arxiv_id":"2008.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrspeech-extremely-low-resource-speech","title":"LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition","date":"2020-08-09","arxiv_id":"2008.03687","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-feature-aggregation-search-for","title":"Differentiable Feature Aggregation Search for Knowledge Distillation","date":"2020-08-02","arxiv_id":"2008.00506","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exclusivity-consistency-regularized-knowledge","title":"Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"local-correlation-consistency-for-knowledge","title":"Local Correlation Consistency for Knowledge Distillation","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-decay-scheduling-and-knowledge","title":"Weight Decay Scheduling and Knowledge Distillation for Active Learning","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-foreground-object-search-as","title":"Interpretable Foreground Object Search As Knowledge Distillation","date":"2020-07-20","arxiv_id":"2007.09867","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-label-contrastive-predictive-coding","title":"Multi-label Contrastive Predictive Coding","date":"2020-07-20","arxiv_id":"2007.09852","repositories_listed":0,"syntology":null},{"url":null,"slug":"covidcare-transferring-knowledge-from","title":"CovidCare: Transferring Knowledge from Existing EMR to Emerging Epidemic for Interpretable Prognosis","date":"2020-07-17","arxiv_id":"2007.08848","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"add-a-sidenet-to-your-mainnet","title":"Add a SideNet to your MainNet","date":"2020-07-14","arxiv_id":"2007.13512","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-teacher-integrating-intra-domain-and","title":"Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentation","date":"2020-07-13","arxiv_id":"2007.06279","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-transfer-by-optimal-transport","title":"Representation Transfer by Optimal Transport","date":"2020-07-13","arxiv_id":"2007.06737","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-ranking-distillation-for-image","title":"Data-Efficient Ranking Distillation for Image Retrieval","date":"2020-07-10","arxiv_id":"2007.05299","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-knowledge-distillation","title":"Interactive Knowledge Distillation","date":"2020-07-03","arxiv_id":"2007.01476","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-beyond-model","title":"Knowledge Distillation Beyond Model Compression","date":"2020-07-03","arxiv_id":"2007.01922","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null}],"record_sha256":"48a342e1c4c74118cd5ac02fbff7e65de36adf9fb35ebf99b6b836a0f46175c8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}