{"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/29","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":29,"pages_in_order":31,"rows_per_page":100,"rows":[2801,2900],"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/28","next":"/method/knowledge-distillation/papers/30","papers":[{"paper":null,"slug":"motion-pyramid-networks-for-accurate-and","title":"Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation","date":"2020-06-28","arxiv_id":"2006.15710","n_code_links":0,"syntology":null},{"paper":null,"slug":"streaming-transformer-asr-with-blockwise","title":"Streaming Transformer ASR with Blockwise Synchronous Inference","date":"2020-06-25","arxiv_id":"2006.14941","n_code_links":0,"syntology":null},{"paper":"/paper/self-knowledge-distillation-a-simple-way-for","slug":"self-knowledge-distillation-a-simple-way-for","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","date":"2020-06-22","arxiv_id":"2006.12000","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":3,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lgcnsai/ps-kd-pytorch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/paying-more-attention-to-snapshots-of","slug":"paying-more-attention-to-snapshots-of","title":"Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation","date":"2020-06-20","arxiv_id":"2006.11487","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":3,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["lehduong/kesi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-fidelity-neural-architecture-search","slug":"multi-fidelity-neural-architecture-search","title":"Multi-fidelity Neural Architecture Search with Knowledge Distillation","date":"2020-06-15","arxiv_id":"2006.08341","n_code_links":1,"syntology":null},{"paper":null,"slug":"pixel-invisibility-detecting-objects","title":"Pixel Invisibility: Detecting Objects Invisible in Color Images","date":"2020-06-15","arxiv_id":"2006.08383","n_code_links":0,"syntology":null},{"paper":"/paper/ensemble-distillation-for-robust-model-fusion","slug":"ensemble-distillation-for-robust-model-fusion","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","date":"2020-06-12","arxiv_id":"2006.07242","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["epfml/federated-learning-public-code"],"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/knowledge-distillation-meets-self-supervision","slug":"knowledge-distillation-meets-self-supervision","title":"Knowledge Distillation Meets Self-Supervision","date":"2020-06-12","arxiv_id":"2006.07114","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xuguodong03/SSKD"],"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/real-time-video-inference-on-edge-devices-via","slug":"real-time-video-inference-on-edge-devices-via","title":"Real-Time Video Inference on Edge Devices via Adaptive Model Streaming","date":"2020-06-11","arxiv_id":"2006.06628","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-a-survey","title":"Knowledge Distillation: A Survey","date":"2020-06-09","arxiv_id":"2006.05525","n_code_links":0,"syntology":null},{"paper":"/paper/classification-under-misspecification","slug":"classification-under-misspecification","title":"Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability","date":"2020-06-08","arxiv_id":"2006.04787","n_code_links":1,"syntology":null},{"paper":"/paper/continual-representation-learning-for","slug":"continual-representation-learning-for","title":"Continual Representation Learning for Biometric Identification","date":"2020-06-08","arxiv_id":"2006.04455","n_code_links":1,"syntology":null},{"paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","slug":"fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","arxiv_id":"2006.04558","n_code_links":37,"syntology":{"ran":83,"of":119,"n_ran_checked":73,"n_instrument":10,"unverified":36,"pointer_only":40,"phrase":"83 ran (of which 27 constructed an object rather than computing a result; 73 with no instrument failure: 9 honoured, 1 violated, 63 with no contract checked; 10 where Syntology's instrument failed) · 36 unverified","official":null}},{"paper":null,"slug":"reskd-residual-guided-knowledge-distillation","title":"ResKD: Residual-Guided Knowledge Distillation","date":"2020-06-08","arxiv_id":"2006.04719","n_code_links":0,"syntology":null},{"paper":null,"slug":"admp-an-adversarial-double-masks-based","title":"ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression","date":"2020-06-07","arxiv_id":"2006.04127","n_code_links":0,"syntology":null},{"paper":"/paper/multi-view-contrastive-learning-for-online","slug":"multi-view-contrastive-learning-for-online","title":"Multi-view Contrastive Learning for Online Knowledge Distillation","date":"2020-06-07","arxiv_id":"2006.04093","n_code_links":1,"syntology":null},{"paper":"/paper/peer-collaborative-learning-for-online","slug":"peer-collaborative-learning-for-online","title":"Peer Collaborative Learning for Online Knowledge Distillation","date":"2020-06-07","arxiv_id":"2006.04147","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"an-overview-of-neural-network-compression","title":"An Overview of Neural Network Compression","date":"2020-06-05","arxiv_id":"2006.03669","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-speech-translation-with-knowledge-1","title":"End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020","date":"2020-06-04","arxiv_id":"2006.02965","n_code_links":0,"syntology":null},{"paper":"/paper/channel-distillation-channel-wise-attention","slug":"channel-distillation-channel-wise-attention","title":"Channel Distillation: Channel-Wise Attention for Knowledge Distillation","date":"2020-06-02","arxiv_id":"2006.01683","n_code_links":1,"syntology":null},{"paper":null,"slug":"adinet-attribute-driven-incremental-network","title":"ADINet: Attribute Driven Incremental Network for Retinal Image Classification","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/distilling-cross-task-knowledge-via","slug":"distilling-cross-task-knowledge-via","title":"Distilling Cross-Task Knowledge via Relationship Matching","date":"2020-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/distilling-image-dehazing-with-heterogeneous","slug":"distilling-image-dehazing-with-heterogeneous","title":"Distilling Image Dehazing With Heterogeneous Task Imitation","date":"2020-06-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/online-knowledge-distillation-via","slug":"online-knowledge-distillation-via","title":"Online Knowledge Distillation via Collaborative Learning","date":"2020-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/transferring-inductive-biases-through","slug":"transferring-inductive-biases-through","title":"Transferring Inductive Biases through Knowledge Distillation","date":"2020-05-31","arxiv_id":"2006.00555","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["samiraabnar/Reflect"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"weight-squeezing-reparameterization-for-1","title":"Weight Squeezing: Reparameterization for Compression and Fast Inference","date":"2020-05-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sub-band-knowledge-distillation-framework-for","title":"Sub-Band Knowledge Distillation Framework for Speech Enhancement","date":"2020-05-29","arxiv_id":"2005.14435","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-structure-distillation-pretraining","title":"Syntactic Structure Distillation Pretraining For Bidirectional Encoders","date":"2020-05-27","arxiv_id":"2005.13482","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-a-lightweight-teacher-for","title":"Learning from a Lightweight Teacher for Efficient Knowledge Distillation","date":"2020-05-19","arxiv_id":"2005.09163","n_code_links":0,"syntology":null},{"paper":"/paper/joint-progressive-knowledge-distillation-and","slug":"joint-progressive-knowledge-distillation-and","title":"Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation","date":"2020-05-16","arxiv_id":"2005.07839","n_code_links":2,"syntology":null},{"paper":null,"slug":"incremental-learning-for-end-to-end-automatic","title":"Incremental Learning for End-to-End Automatic Speech Recognition","date":"2020-05-11","arxiv_id":"2005.04288","n_code_links":0,"syntology":null},{"paper":"/paper/maze-data-free-model-stealing-attack-using","slug":"maze-data-free-model-stealing-attack-using","title":"MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation","date":"2020-05-06","arxiv_id":"2005.03161","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-neural-machine","title":"Improving Non-autoregressive Neural Machine Translation with Monolingual Data","date":"2020-05-02","arxiv_id":"2005.00932","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-spikes-knowledge-distillation-in","title":"Distilling Spikes: Knowledge Distillation in Spiking Neural Networks","date":"2020-05-01","arxiv_id":"2005.00288","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightpaff-a-two-stage-distillation-framework-1","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","date":"2020-04-27","arxiv_id":"2004.12817","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-knowledge-from-refinement-in","slug":"distilling-knowledge-from-refinement-in","title":"Distilling Knowledge from Refinement in Multiple Instance Detection Networks","date":"2020-04-23","arxiv_id":"2004.10943","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-non-autoregressive-model-for","title":"A Study of Non-autoregressive Model for Sequence Generation","date":"2020-04-22","arxiv_id":"2004.10454","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-multilingual","title":"Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation","date":"2020-04-21","arxiv_id":"2004.10171","n_code_links":0,"syntology":null},{"paper":"/paper/triplet-loss-for-knowledge-distillation","slug":"triplet-loss-for-knowledge-distillation","title":"Triplet Loss for Knowledge Distillation","date":"2020-04-17","arxiv_id":"2004.08116","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-action","title":"Knowledge Distillation for Action Anticipation via Label Smoothing","date":"2020-04-16","arxiv_id":"2004.07711","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-and-multiview-distillation-for","slug":"multimodal-and-multiview-distillation-for","title":"Multimodal and multiview distillation for real-time player detection on a football field","date":"2020-04-16","arxiv_id":"2004.07544","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-multi-domain-neural-machine","title":"Building a Multi-domain Neural Machine Translation Model using Knowledge Distillation","date":"2020-04-15","arxiv_id":"2004.07324","n_code_links":0,"syntology":null},{"paper":"/paper/dark-experience-for-general-continual","slug":"dark-experience-for-general-continual","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","date":"2020-04-15","arxiv_id":"2004.07211","n_code_links":3,"syntology":null},{"paper":null,"slug":"smart-inference-for-multidigit-convolutional","title":"Smart Inference for Multidigit Convolutional Neural Network based Barcode Decoding","date":"2020-04-14","arxiv_id":"2004.06297","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-classification-with-image","title":"Towards Robust Classification with Image Quality Assessment","date":"2020-04-14","arxiv_id":"2004.06288","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-distillation-and-student-teacher","slug":"knowledge-distillation-and-student-teacher","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","date":"2020-04-13","arxiv_id":"2004.05937","n_code_links":2,"syntology":null},{"paper":null,"slug":"tinymbert-multi-stage-distillation-framework","title":"XtremeDistil: Multi-stage Distillation for Massive Multilingual Models","date":"2020-04-12","arxiv_id":"2004.05686","n_code_links":0,"syntology":null},{"paper":"/paper/inter-region-affinity-distillation-for-road","slug":"inter-region-affinity-distillation-for-road","title":"Inter-Region Affinity Distillation for Road Marking Segmentation","date":"2020-04-11","arxiv_id":"2004.05304","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["cardwing/Codes-for-IntRA-KD"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/kd-mri-a-knowledge-distillation-framework-for","slug":"kd-mri-a-knowledge-distillation-framework-for","title":"KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow","date":"2020-04-11","arxiv_id":"2004.05319","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-mobile-edge","title":"Knowledge Distillation for Mobile Edge Computation Offloading","date":"2020-04-09","arxiv_id":"2004.04366","n_code_links":0,"syntology":null},{"paper":null,"slug":"ladabert-lightweight-adaptation-of-bert","title":"LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression","date":"2020-04-08","arxiv_id":"2004.04124","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-task-specific-distillation-of","title":"Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation","date":"2020-04-07","arxiv_id":"2004.03097","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-review-comprehension-with-domain","title":"Enhancing Review Comprehension with Domain-Specific Commonsense","date":"2020-04-06","arxiv_id":"2004.03020","n_code_links":0,"syntology":null},{"paper":"/paper/temporally-distributed-networks-for-fast","slug":"temporally-distributed-networks-for-fast","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","date":"2020-04-03","arxiv_id":"2004.01800","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"knowledge-as-priors-cross-modal-knowledge","title":"Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge","date":"2020-04-01","arxiv_id":"2004.00176","n_code_links":0,"syntology":null},{"paper":"/paper/more-grounded-image-captioning-by-distilling","slug":"more-grounded-image-captioning-by-distilling","title":"More Grounded Image Captioning by Distilling Image-Text Matching Model","date":"2020-04-01","arxiv_id":"2004.00390","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["YuanEZhou/Grounded-Image-Captioning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-simple-class-decision-balancing-for","title":"SS-IL: Separated Softmax for Incremental Learning","date":"2020-03-31","arxiv_id":"2003.13947","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-semantics-for-comprehensive-scene","slug":"distilled-semantics-for-comprehensive-scene","title":"Distilled Semantics for Comprehensive Scene Understanding from Videos","date":"2020-03-31","arxiv_id":"2003.14030","n_code_links":1,"syntology":null},{"paper":"/paper/neural-networks-are-more-productive-teachers","slug":"neural-networks-are-more-productive-teachers","title":"Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model","date":"2020-03-31","arxiv_id":"2003.13960","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatio-temporal-graph-for-video-captioning","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","date":"2020-03-31","arxiv_id":"2003.13942","n_code_links":0,"syntology":null},{"paper":"/paper/squeezed-deep-6dof-object-detection-using","slug":"squeezed-deep-6dof-object-detection-using","title":"Squeezed Deep 6DoF Object Detection Using Knowledge Distillation","date":"2020-03-30","arxiv_id":"2003.13586","n_code_links":2,"syntology":null},{"paper":"/paper/circumventing-outliers-of-autoaugment-with","slug":"circumventing-outliers-of-autoaugment-with","title":"Circumventing Outliers of AutoAugment with Knowledge Distillation","date":"2020-03-25","arxiv_id":"2003.11342","n_code_links":1,"syntology":null},{"paper":null,"slug":"synergic-adversarial-label-learning-with-dr","title":"Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning","date":"2020-03-24","arxiv_id":"2003.10607","n_code_links":0,"syntology":null},{"paper":"/paper/distillating-knowledge-from-graph","slug":"distillating-knowledge-from-graph","title":"Distilling Knowledge from Graph Convolutional Networks","date":"2020-03-23","arxiv_id":"2003.10477","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ihollywhy/DistillGCN.PyTorch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/collaborative-distillation-for-ultra","slug":"collaborative-distillation-for-ultra","title":"Collaborative Distillation for Ultra-Resolution Universal Style Transfer","date":"2020-03-18","arxiv_id":"2003.08436","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mingsun-tse/collaborative-distillation"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/incremental-object-detection-via-meta","slug":"incremental-object-detection-via-meta","title":"Incremental Object Detection via Meta-Learning","date":"2020-03-17","arxiv_id":"2003.08798","n_code_links":2,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["JosephKJ/iOD"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"teacher-student-chain-for-efficient-semi","title":"Teacher-Student chain for efficient semi-supervised histology image classification","date":"2020-03-17","arxiv_id":"2003.08797","n_code_links":0,"syntology":null},{"paper":"/paper/deformation-flow-based-two-stream-network-for","slug":"deformation-flow-based-two-stream-network-for","title":"Deformation Flow Based Two-Stream Network for Lip Reading","date":"2020-03-12","arxiv_id":"2003.05709","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-via-adaptive-instance","title":"Knowledge distillation via adaptive instance normalization","date":"2020-03-09","arxiv_id":"2003.04289","n_code_links":0,"syntology":null},{"paper":null,"slug":"pacemaker-intermediate-teacher-knowledge","title":"Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network","date":"2020-03-09","arxiv_id":"2003.03944","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-knowledge-distillation-by","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","date":"2020-03-07","arxiv_id":"2003.03622","n_code_links":0,"syntology":null},{"paper":null,"slug":"distill-adapt-distill-training-small-in","title":"Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation","date":"2020-03-05","arxiv_id":"2003.02877","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-method-of-training-small-models","title":"An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation","date":"2020-02-28","arxiv_id":"2002.12597","n_code_links":0,"syntology":null},{"paper":"/paper/textbrewer-an-open-source-knowledge","slug":"textbrewer-an-open-source-knowledge","title":"TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing","date":"2020-02-28","arxiv_id":"2002.12620","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-semantic-video-segmentation-with","slug":"efficient-semantic-video-segmentation-with","title":"Efficient Semantic Video Segmentation with Per-frame Inference","date":"2020-02-26","arxiv_id":"2002.11433","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/semi-supervised-speech-recognition-via-local","slug":"semi-supervised-speech-recognition-via-local","title":"Semi-Supervised Speech Recognition via Local Prior Matching","date":"2020-02-24","arxiv_id":"2002.10336","n_code_links":1,"syntology":null},{"paper":null,"slug":"residual-knowledge-distillation","title":"Residual Knowledge Distillation","date":"2020-02-21","arxiv_id":"2002.09168","n_code_links":0,"syntology":null},{"paper":null,"slug":"balancing-cost-and-benefit-with-tied-multi-1","title":"Balancing Cost and Benefit with Tied-Multi Transformers","date":"2020-02-20","arxiv_id":"2002.08614","n_code_links":0,"syntology":null},{"paper":"/paper/knapsack-pruning-with-inner-distillation","slug":"knapsack-pruning-with-inner-distillation","title":"Knapsack Pruning with Inner Distillation","date":"2020-02-19","arxiv_id":"2002.08258","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yoniaflalo/knapsack_pruning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/content-based-singing-voice-extraction-from-a","slug":"content-based-singing-voice-extraction-from-a","title":"Content Based Singing Voice Extraction From a Musical Mixture","date":"2020-02-12","arxiv_id":"2002.04933","n_code_links":1,"syntology":null},{"paper":null,"slug":"population-based-training-for-loss-function","title":"Regularized Evolutionary Population-Based Training","date":"2020-02-11","arxiv_id":"2002.04225","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlabeled-data-deployment-for-classification","title":"Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer","date":"2020-02-09","arxiv_id":"2002.03321","n_code_links":0,"syntology":null},{"paper":"/paper/suod-toward-scalable-unsupervised-outlier","slug":"suod-toward-scalable-unsupervised-outlier","title":"SUOD: Toward Scalable Unsupervised Outlier Detection","date":"2020-02-08","arxiv_id":"2002.03222","n_code_links":2,"syntology":null},{"paper":"/paper/bert-of-theseus-compressing-bert-by","slug":"bert-of-theseus-compressing-bert-by","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","date":"2020-02-07","arxiv_id":"2002.02925","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":1,"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":["JetRunner/BERT-of-Theseus"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"feature-map-level-online-adversarial-1","title":"Feature-map-level Online Adversarial Knowledge Distillation","date":"2020-02-05","arxiv_id":"2002.01775","n_code_links":0,"syntology":null},{"paper":"/paper/periodic-intra-ensemble-knowledge","slug":"periodic-intra-ensemble-knowledge","title":"Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning","date":"2020-02-01","arxiv_id":"2002.00149","n_code_links":1,"syntology":null},{"paper":"/paper/mse-optimal-neural-network-initialization-via","slug":"mse-optimal-neural-network-initialization-via","title":"MSE-Optimal Neural Network Initialization via Layer Fusion","date":"2020-01-28","arxiv_id":"2001.10509","n_code_links":1,"syntology":null},{"paper":null,"slug":"developing-multi-task-recommendations-with","title":"Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning","date":"2020-01-27","arxiv_id":"2001.09595","n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-distillation-for-efficient-natural-1","title":"Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings","date":"2020-01-25","arxiv_id":"2002.00733","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-techniques-for-online-end-to-end-speech","title":"Data Techniques For Online End-to-end Speech Recognition","date":"2020-01-24","arxiv_id":"2001.09221","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-3d-human-pose-estimation-network","title":"Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning","date":"2020-01-15","arxiv_id":"2001.05097","n_code_links":0,"syntology":null},{"paper":null,"slug":"noisy-machines-understanding-noisy-neural-1","title":"Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation","date":"2020-01-14","arxiv_id":"2001.04974","n_code_links":0,"syntology":null},{"paper":"/paper/adabert-task-adaptive-bert-compression-with","slug":"adabert-task-adaptive-bert-compression-with","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","date":"2020-01-13","arxiv_id":"2001.04246","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":"/paper/learning-from-multiple-experts-self-paced","slug":"learning-from-multiple-experts-self-paced","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","date":"2020-01-06","arxiv_id":"2001.01536","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-task-agnostic-embedding-of-multiple","title":"Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"degan-data-enriching-gan-for-retrieving","title":"DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier","date":"2019-12-27","arxiv_id":"1912.11960","n_code_links":0,"syntology":null},{"paper":"/paper/the-state-of-knowledge-distillation-for","slug":"the-state-of-knowledge-distillation-for","title":"The State of Knowledge Distillation for Classification","date":"2019-12-20","arxiv_id":"1912.10850","n_code_links":1,"syntology":null},{"paper":null,"slug":"joint-architecture-and-knowledge-distillation","title":"Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition","date":"2019-12-17","arxiv_id":"1912.07806","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-dual-domain-adaptation-for-neural-1","title":"Iterative Dual Domain Adaptation for Neural Machine Translation","date":"2019-12-16","arxiv_id":"1912.07239","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-sequence-level-knowledge","title":"Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation","date":"2019-12-06","arxiv_id":"1912.03334","n_code_links":0,"syntology":null}],"record_sha256":"563d03de0a10f96a8e29cf3ba850eecf6f23b8145f631ae7171c3c8420f21b84","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}