{"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/22","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":22,"pages_in_order":31,"rows_per_page":100,"rows":[2101,2200],"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/21","next":"/method/knowledge-distillation/papers/23","papers":[{"paper":"/paper/cross-modal-perceptionist-can-face-geometry","slug":"cross-modal-perceptionist-can-face-geometry","title":"Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?","date":"2022-03-18","arxiv_id":"2203.09824","n_code_links":1,"syntology":null},{"paper":"/paper/delta-distillation-for-efficient-video","slug":"delta-distillation-for-efficient-video","title":"Delta Distillation for Efficient Video Processing","date":"2022-03-17","arxiv_id":"2203.09594","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-global-model-via-data-free","slug":"fine-tuning-global-model-via-data-free","title":"Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning","date":"2022-03-17","arxiv_id":"2203.09249","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["zhanglin-pku/fedftg"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/when-chosen-wisely-more-data-is-what-you-need-1","slug":"when-chosen-wisely-more-data-is-what-you-need-1","title":"When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation","date":"2022-03-17","arxiv_id":"2203.09391","n_code_links":1,"syntology":null},{"paper":"/paper/decoupled-knowledge-distillation","slug":"decoupled-knowledge-distillation","title":"Decoupled Knowledge Distillation","date":"2022-03-16","arxiv_id":"2203.08679","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["megvii-research/mdistiller"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-flow-cross-layer-graph-flow","slug":"graph-flow-cross-layer-graph-flow","title":"Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation","date":"2022-03-16","arxiv_id":"2203.08667","n_code_links":1,"syntology":null},{"paper":null,"slug":"sample-translate-recombine-leveraging-audio","title":"Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation","date":"2022-03-16","arxiv_id":"2203.08757","n_code_links":0,"syntology":null},{"paper":"/paper/sc2-supervised-compression-for-split","slug":"sc2-supervised-compression-for-split","title":"SC2 Benchmark: Supervised Compression for Split Computing","date":"2022-03-16","arxiv_id":"2203.08875","n_code_links":1,"syntology":null},{"paper":"/paper/sats-self-attention-transfer-for-continual","slug":"sats-self-attention-transfer-for-continual","title":"SATS: Self-Attention Transfer for Continual Semantic Segmentation","date":"2022-03-15","arxiv_id":"2203.07667","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-benefits-of-knowledge-distillation-for","title":"On the benefits of knowledge distillation for adversarial robustness","date":"2022-03-14","arxiv_id":"2203.07159","n_code_links":0,"syntology":null},{"paper":null,"slug":"cekd-cross-ensemble-knowledge-distillation","title":"CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data","date":"2022-03-13","arxiv_id":"2203.06551","n_code_links":0,"syntology":null},{"paper":"/paper/cmkd-cnn-transformer-based-cross-model","slug":"cmkd-cnn-transformer-based-cross-model","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","date":"2022-03-13","arxiv_id":"2203.06760","n_code_links":2,"syntology":null},{"paper":null,"slug":"enabling-multimodal-generation-on-clip-via-1","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2022-03-12","arxiv_id":"2203.06386","n_code_links":0,"syntology":null},{"paper":null,"slug":"wavelet-knowledge-distillation-towards","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","date":"2022-03-12","arxiv_id":"2203.06321","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-class-incremental-learning-from","title":"Deep Class Incremental Learning from Decentralized Data","date":"2022-03-11","arxiv_id":"2203.05984","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-image-segmentation-on-mri-images-with","title":"Medical Image Segmentation on MRI Images with Missing Modalities: A Review","date":"2022-03-11","arxiv_id":"2203.06217","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neural-odes-via-knowledge","title":"Improving Neural ODEs via Knowledge Distillation","date":"2022-03-10","arxiv_id":"2203.05103","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-distillation-as-efficient-pre","slug":"knowledge-distillation-as-efficient-pre","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","date":"2022-03-10","arxiv_id":"2203.05180","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":3,"n_instrument":6,"unverified":4,"pointer_only":3,"phrase":"9 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["cvmi-lab/kdep"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"membership-privacy-protection-for-image","title":"Membership Privacy Protection for Image Translation Models via Adversarial Knowledge Distillation","date":"2022-03-10","arxiv_id":"2203.05212","n_code_links":0,"syntology":null},{"paper":"/paper/model-architecture-co-design-for-high","slug":"model-architecture-co-design-for-high","title":"Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA","date":"2022-03-10","arxiv_id":"2203.05095","n_code_links":1,"syntology":null},{"paper":"/paper/prediction-guided-distillation-for-dense","slug":"prediction-guided-distillation-for-dense","title":"Prediction-Guided Distillation for Dense Object Detection","date":"2022-03-10","arxiv_id":"2203.05469","n_code_links":1,"syntology":null},{"paper":"/paper/representation-compensation-networks-for","slug":"representation-compensation-networks-for","title":"Representation Compensation Networks for Continual Semantic Segmentation","date":"2022-03-10","arxiv_id":"2203.05402","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["zhangchbin/rcil"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/efficient-sub-structured-knowledge","slug":"efficient-sub-structured-knowledge","title":"Efficient Sub-structured Knowledge Distillation","date":"2022-03-09","arxiv_id":"2203.04825","n_code_links":1,"syntology":null},{"paper":"/paper/overcoming-catastrophic-forgetting-beyond","slug":"overcoming-catastrophic-forgetting-beyond","title":"Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation","date":"2022-03-08","arxiv_id":"2203.03910","n_code_links":1,"syntology":null},{"paper":"/paper/pynet-qxq-a-distilled-pynet-for-qxq-bayer","slug":"pynet-qxq-a-distilled-pynet-for-qxq-bayer","title":"PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors","date":"2022-03-08","arxiv_id":"2203.04314","n_code_links":1,"syntology":null},{"paper":null,"slug":"uenas-a-unified-evolution-based-nas-framework","title":"Multi-trial Neural Architecture Search with Lottery Tickets","date":"2022-03-08","arxiv_id":"2203.04300","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-language-identification-using-dual","slug":"enhance-language-identification-using-dual","title":"Enhance Language Identification using Dual-mode Model with Knowledge Distillation","date":"2022-03-07","arxiv_id":"2203.03218","n_code_links":1,"syntology":null},{"paper":"/paper/student-become-decathlon-master-in-retinal","slug":"student-become-decathlon-master-in-retinal","title":"Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain Adaptation","date":"2022-03-07","arxiv_id":"2203.03631","n_code_links":1,"syntology":null},{"paper":"/paper/consistent-representation-learning-for","slug":"consistent-representation-learning-for","title":"Consistent Representation Learning for Continual Relation Extraction","date":"2022-03-05","arxiv_id":"2203.02721","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":6,"n_instrument":1,"unverified":5,"pointer_only":12,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["thuiar/CRL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/better-supervisory-signals-by-observing-1","slug":"better-supervisory-signals-by-observing-1","title":"Better Supervisory Signals by Observing Learning Paths","date":"2022-03-04","arxiv_id":"2203.02485","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["joshua-ren/better_supervisory_signal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/x-trans2cap-cross-modal-knowledge-transfer","slug":"x-trans2cap-cross-modal-knowledge-transfer","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","date":"2022-03-02","arxiv_id":"2203.00843","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-embodied-symbolic-concept","title":"Dual Embodied-Symbolic Concept Representations for Deep Learning","date":"2022-03-01","arxiv_id":"2203.00600","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-vision-transformers-learn","slug":"self-supervised-vision-transformers-learn","title":"Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology","date":"2022-03-01","arxiv_id":"2203.00585","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-knowledge-distillation-for","slug":"transformer-based-knowledge-distillation-for","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","date":"2022-02-27","arxiv_id":"2202.13393","n_code_links":2,"syntology":null},{"paper":"/paper/content-variant-reference-image-quality","slug":"content-variant-reference-image-quality","title":"Content-Variant Reference Image Quality Assessment via Knowledge Distillation","date":"2022-02-26","arxiv_id":"2202.13123","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":{"repos":["guanghaoyin/cvrkd-iqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-the-gap-between-patient-specific-and","title":"Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation","date":"2022-02-25","arxiv_id":"2202.12598","n_code_links":0,"syntology":null},{"paper":"/paper/joint-answering-and-explanation-for-visual","slug":"joint-answering-and-explanation-for-visual","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","date":"2022-02-25","arxiv_id":"2202.12626","n_code_links":1,"syntology":null},{"paper":null,"slug":"learn-from-the-past-experience-ensemble","title":"Learn From the Past: Experience Ensemble Knowledge Distillation","date":"2022-02-25","arxiv_id":"2202.12488","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-video-segmentation-models-with-per","title":"Efficient Video Segmentation Models with Per-frame Inference","date":"2022-02-24","arxiv_id":"2202.12427","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-teacher-knowledge-distillation-for","title":"Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification","date":"2022-02-23","arxiv_id":"2202.11384","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-neural-networks-for-efficient","slug":"distilled-neural-networks-for-efficient","title":"Distilled Neural Networks for Efficient Learning to Rank","date":"2022-02-22","arxiv_id":"2202.10728","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-architecture-slimming-method-for","title":"A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation","date":"2022-02-21","arxiv_id":"2202.10461","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-task-knowledge-distillation-in-multi","title":"Cross-Task Knowledge Distillation in Multi-Task Recommendation","date":"2022-02-20","arxiv_id":"2202.09852","n_code_links":0,"syntology":null},{"paper":null,"slug":"deeply-supervised-knowledge-distillation","title":"Knowledge Distillation with Deep Supervision","date":"2022-02-16","arxiv_id":"2202.07846","n_code_links":0,"syntology":null},{"paper":"/paper/edgeformer-a-parameter-efficient-transformer","slug":"edgeformer-a-parameter-efficient-transformer","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","date":"2022-02-16","arxiv_id":"2202.07959","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":["microsoft/unilm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/famie-a-fast-active-learning-framework-for","slug":"famie-a-fast-active-learning-framework-for","title":"FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction","date":"2022-02-16","arxiv_id":"2202.08316","n_code_links":1,"syntology":null},{"paper":"/paper/meta-knowledge-distillation","slug":"meta-knowledge-distillation","title":"Meta Knowledge Distillation","date":"2022-02-16","arxiv_id":"2202.07940","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-one-left-behind-inclusive-federated","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","date":"2022-02-16","arxiv_id":"2202.08036","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-can-evolve-without-labels-self-evolving","title":"AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation","date":"2022-02-13","arxiv_id":"2202.06431","n_code_links":0,"syntology":null},{"paper":null,"slug":"uni-retriever-towards-learning-the-unified","title":"Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search","date":"2022-02-13","arxiv_id":"2202.06212","n_code_links":0,"syntology":null},{"paper":"/paper/tiny-object-tracking-a-large-scale-dataset","slug":"tiny-object-tracking-a-large-scale-dataset","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","date":"2022-02-11","arxiv_id":"2202.05659","n_code_links":1,"syntology":null},{"paper":null,"slug":"distillation-with-contrast-is-all-you-need","title":"Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning","date":"2022-02-09","arxiv_id":"2202.04241","n_code_links":0,"syntology":null},{"paper":"/paper/point-level-region-contrast-for-object","slug":"point-level-region-contrast-for-object","title":"Point-Level Region Contrast for Object Detection Pre-Training","date":"2022-02-09","arxiv_id":"2202.04639","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["facebookresearch/PLRC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-inter-channel-correlation-for-1","slug":"exploring-inter-channel-correlation-for-1","title":"Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation","date":"2022-02-08","arxiv_id":"2202.03680","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["adlab-autodrive/ickd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/alm-kd-knowledge-distillation-with-noisy","slug":"alm-kd-knowledge-distillation-with-noisy","title":"Adaptive Mixing of Auxiliary Losses in Supervised Learning","date":"2022-02-07","arxiv_id":"2202.03250","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-and-reducing-model-update","title":"Measuring and Reducing Model Update Regression in Structured Prediction for NLP","date":"2022-02-07","arxiv_id":"2202.02976","n_code_links":0,"syntology":null},{"paper":null,"slug":"bootstrapped-representation-learning-for","title":"Bootstrapped Representation Learning for Skeleton-Based Action Recognition","date":"2022-02-04","arxiv_id":"2202.02232","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-knowledge-compression-in","title":"Cross domain knowledge compression in realtime optical flow prediction on ultrasound sequences","date":"2022-02-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-self-knowledge-distillation-from","title":"Iterative Self Knowledge Distillation -- From Pothole Classification to Fine-Grained and COVID Recognition","date":"2022-02-04","arxiv_id":"2202.02265","n_code_links":0,"syntology":null},{"paper":"/paper/local-feature-matching-with-transformers-for","slug":"local-feature-matching-with-transformers-for","title":"Local Feature Matching with Transformers for low-end devices","date":"2022-02-01","arxiv_id":"2202.00770","n_code_links":1,"syntology":null},{"paper":"/paper/deep-disaster-unsupervised-disaster-detection","slug":"deep-disaster-unsupervised-disaster-detection","title":"Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data","date":"2022-01-31","arxiv_id":"2202.00050","n_code_links":1,"syntology":null},{"paper":"/paper/improving-corruption-and-adversarial","slug":"improving-corruption-and-adversarial","title":"Improving Robustness by Enhancing Weak Subnets","date":"2022-01-30","arxiv_id":"2201.12765","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["guoyongcs/ews"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"win-the-lottery-ticket-via-fourier-analysis","title":"Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning","date":"2022-01-30","arxiv_id":"2201.12712","n_code_links":0,"syntology":null},{"paper":"/paper/global-reasoned-multi-task-learning-model-for","slug":"global-reasoned-multi-task-learning-model-for","title":"Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding","date":"2022-01-28","arxiv_id":"2201.11957","n_code_links":2,"syntology":{"ran":1,"of":8,"n_ran_checked":0,"n_instrument":1,"unverified":7,"pointer_only":8,"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) · 7 unverified","official":{"repos":["lalithjets/global-reasoned-multi-task-model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-rectification-knowledge-distillation","slug":"dynamic-rectification-knowledge-distillation","title":"Dynamic Rectification Knowledge Distillation","date":"2022-01-27","arxiv_id":"2201.11319","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-instance-distillation-for-object","title":"Adaptive Instance Distillation for Object Detection in Autonomous Driving","date":"2022-01-26","arxiv_id":"2201.11097","n_code_links":0,"syntology":null},{"paper":"/paper/anomaly-detection-via-reverse-distillation","slug":"anomaly-detection-via-reverse-distillation","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","date":"2022-01-26","arxiv_id":"2201.10703","n_code_links":5,"syntology":{"ran":14,"of":18,"n_ran_checked":10,"n_instrument":4,"unverified":4,"pointer_only":15,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["hq-deng/RD4AD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"one-student-knows-all-experts-know-from","title":"One Student Knows All Experts Know: From Sparse to Dense","date":"2022-01-26","arxiv_id":"2201.10890","n_code_links":0,"syntology":null},{"paper":"/paper/attentive-task-interaction-network-for-multi","slug":"attentive-task-interaction-network-for-multi","title":"Attentive Task Interaction Network for Multi-Task Learning","date":"2022-01-25","arxiv_id":"2201.10649","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-learning-knowledge-embedding-and","title":"Jointly Learning Knowledge Embedding and Neighborhood Consensus with Relational Knowledge Distillation for Entity Alignment","date":"2022-01-25","arxiv_id":"2201.11249","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-unlearning-with-knowledge","title":"Federated Unlearning with Knowledge Distillation","date":"2022-01-24","arxiv_id":"2201.09441","n_code_links":0,"syntology":null},{"paper":null,"slug":"autodistill-an-end-to-end-framework-to","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","date":"2022-01-21","arxiv_id":"2201.08539","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-model-compression-improve-nlp-fairness","title":"Can Model Compression Improve NLP Fairness","date":"2022-01-21","arxiv_id":"2201.08542","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-to-video-re-identification-via-mutual","title":"Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer","date":"2022-01-21","arxiv_id":"2201.08887","n_code_links":0,"syntology":null},{"paper":null,"slug":"ukd-debiasing-conversion-rate-estimation-via","title":"UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation","date":"2022-01-20","arxiv_id":"2201.08024","n_code_links":0,"syntology":null},{"paper":"/paper/continual-coarse-to-fine-domain-adaptation-in","slug":"continual-coarse-to-fine-domain-adaptation-in","title":"Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation","date":"2022-01-18","arxiv_id":"2201.06974","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-modal-contrastive-distillation-for","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","date":"2022-01-18","arxiv_id":"2201.06734","n_code_links":0,"syntology":null},{"paper":"/paper/it-s-all-in-the-head-representation-knowledge","slug":"it-s-all-in-the-head-representation-knowledge","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","date":"2022-01-18","arxiv_id":"2201.06945","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-as-self-supervised","title":"Knowledge Distillation as Self-Supervised Learning","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cl-rekd-cross-lingual-knowledge-distillation","title":"CL-ReKD: Cross-lingual Knowledge Distillation for Multilingual Retrieval Question Answering","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kd-vlp-improving-end-to-end-vision-and-1","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-cross-lingual-ir-from-an-english-1","title":"Learning Cross-Lingual IR from an English Retriever","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nearest-neighbor-knowledge-distillation-for","title":"Nearest Neighbor Knowledge Distillation for Neural Machine Translation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-knowledge-from-structure-aware","title":"Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-knowledge-distillation-for-compressing","title":"Tree Knowledge Distillation for Compressing Transformer-Based Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/simreg-regression-as-a-simple-yet-effective","slug":"simreg-regression-as-a-simple-yet-effective","title":"SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation","date":"2022-01-13","arxiv_id":"2201.05131","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":10,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ucdvision/simreg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"technical-report-for-iccv-2021-challenge","title":"Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners","date":"2022-01-13","arxiv_id":"2201.04924","n_code_links":0,"syntology":null},{"paper":"/paper/on-exploring-pose-estimation-as-an-auxiliary","slug":"on-exploring-pose-estimation-as-an-auxiliary","title":"On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification","date":"2022-01-11","arxiv_id":"2201.03859","n_code_links":1,"syntology":null},{"paper":null,"slug":"feddtg-federated-data-free-knowledge","title":"FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks","date":"2022-01-10","arxiv_id":"2201.03169","n_code_links":0,"syntology":null},{"paper":"/paper/robust-and-resource-efficient-data-free","slug":"robust-and-resource-efficient-data-free","title":"Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay","date":"2022-01-09","arxiv_id":"2201.03019","n_code_links":1,"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":["kuluhan/pre-dfkd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"two-pass-end-to-end-asr-model-compression","title":"Two-Pass End-to-End ASR Model Compression","date":"2022-01-08","arxiv_id":"2201.02741","n_code_links":0,"syntology":null},{"paper":null,"slug":"microdosing-knowledge-distillation-for-gan","title":"Microdosing: Knowledge Distillation for GAN based Compression","date":"2022-01-07","arxiv_id":"2201.02624","n_code_links":0,"syntology":null},{"paper":"/paper/class-incremental-continual-learning-into-the","slug":"class-incremental-continual-learning-into-the","title":"Class-Incremental Continual Learning into the eXtended DER-verse","date":"2022-01-03","arxiv_id":"2201.00766","n_code_links":1,"syntology":null},{"paper":null,"slug":"which-student-is-best-a-comprehensive","title":"Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models","date":"2022-01-03","arxiv_id":"2201.00558","n_code_links":0,"syntology":null},{"paper":null,"slug":"class-similarity-weighted-knowledge","title":"Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"distillation-using-oracle-queries-for","title":"Distillation Using Oracle Queries for Transformer-Based Human-Object Interaction Detection","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"image-restoration-using-feature-guidance","title":"Image Restoration using Feature-guidance","date":"2022-01-01","arxiv_id":"2201.00187","n_code_links":0,"syntology":null},{"paper":"/paper/learn-from-others-and-be-yourself-in","slug":"learn-from-others-and-be-yourself-in","title":"Learn From Others and Be Yourself in Heterogeneous Federated Learning","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-aware-mutual-knowledge","title":"Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"c96f999c6e0b21b12d786d93c29b7aeed6407fc3b7a83f59fb08eaa48e258929","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}