{"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/35","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":35,"pages_in_order":43,"rows_per_page":100,"rows":[3401,3500],"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/34","next":"/task/knowledge-distillation/papers/36","papers":[{"url":null,"slug":"multitask-emotion-recognition-model-with","title":"Multitask Emotion Recognition Model with Knowledge Distillation and Task Discriminator","date":"2022-03-24","arxiv_id":"2203.13072","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-gender-bias-in-distilled-language","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","date":"2022-03-23","arxiv_id":"2203.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"scale-equivalent-distillation-for-semi","title":"Scale-Equivalent Distillation for Semi-Supervised Object Detection","date":"2022-03-23","arxiv_id":"2203.12244","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-expressive-speaking-style-modelling","title":"Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis","date":"2022-03-23","arxiv_id":"2203.12201","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-self-supervision-for-online-knowledge","title":"Channel Self-Supervision for Online Knowledge Distillation","date":"2022-03-22","arxiv_id":"2203.11660","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-neural-network-equivalence-checking-using","title":"On Neural Network Equivalence Checking using SMT Solvers","date":"2022-03-22","arxiv_id":"2203.11629","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-knowledge-distillation-with","title":"A Closer Look at Knowledge Distillation with Features, Logits, and Gradients","date":"2022-03-18","arxiv_id":"2203.10163","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptive-hand-keypoint-and-pixel","title":"Domain Adaptive Hand Keypoint and Pixel Localization in the Wild","date":"2022-03-16","arxiv_id":"2203.08344","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"ds3-net-difficulty-perceived-common-to-t1ce","title":"DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network","date":"2022-03-14","arxiv_id":"2203.06920","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelet-knowledge-distillation-towards","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","date":"2022-03-12","arxiv_id":"2203.06321","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-class-incremental-learning-from","title":"Deep Class Incremental Learning from Decentralized Data","date":"2022-03-11","arxiv_id":"2203.05984","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-neural-odes-via-knowledge","title":"Improving Neural ODEs via Knowledge Distillation","date":"2022-03-10","arxiv_id":"2203.05103","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-backward-and-forward-self-knowledge","title":"Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation","date":"2022-03-10","arxiv_id":"2203.05248","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-many-observations-are-enough-knowledge","title":"How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting","date":"2022-03-09","arxiv_id":"2203.04781","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-generalizing-beyond-domains-in-cross","title":"On Generalizing Beyond Domains in Cross-Domain Continual Learning","date":"2022-03-08","arxiv_id":"2203.03970","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"miashield-defending-membership-inference","title":"MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members","date":"2022-03-02","arxiv_id":"2203.00915","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-embodied-symbolic-concept","title":"Dual Embodied-Symbolic Concept Representations for Deep Learning","date":"2022-03-01","arxiv_id":"2203.00600","repositories_listed":0,"syntology":null},{"url":null,"slug":"trillsson-distilled-universal-paralinguistic","title":"TRILLsson: Distilled Universal Paralinguistic Speech Representations","date":"2022-03-01","arxiv_id":"2203.00236","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-based-bidirectional-global-context","title":"Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation","date":"2022-02-28","arxiv_id":"2202.13663","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":"/paper/learning-bayesian-sparse-networks-with-full","slug":"learning-bayesian-sparse-networks-with-full","title":"Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning","date":"2022-02-21","arxiv_id":"2202.10203","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeply-supervised-knowledge-distillation","title":"Knowledge Distillation with Deep Supervision","date":"2022-02-16","arxiv_id":"2202.07846","repositories_listed":0,"syntology":null},{"url":"/paper/meta-knowledge-distillation","slug":"meta-knowledge-distillation","title":"Meta Knowledge Distillation","date":"2022-02-16","arxiv_id":"2202.07940","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapped-representation-learning-for","title":"Bootstrapped Representation Learning for Skeleton-Based Action Recognition","date":"2022-02-04","arxiv_id":"2202.02232","repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"autodistil-few-shot-task-agnostic-neural","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","date":"2022-01-29","arxiv_id":"2201.12507","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"trustal-trustworthy-active-learning-using","title":"TrustAL: Trustworthy Active Learning using Knowledge Distillation","date":"2022-01-26","arxiv_id":"2201.11661","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-unlearning-with-knowledge","title":"Federated Unlearning with Knowledge Distillation","date":"2022-01-24","arxiv_id":"2201.09441","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-model-compression-improve-nlp-fairness","title":"Can Model Compression Improve NLP Fairness","date":"2022-01-21","arxiv_id":"2201.08542","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-neural-machine-translation-by-3","title":"Improving Neural Machine Translation by Denoising Training","date":"2022-01-19","arxiv_id":"2201.07365","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-contrastive-distillation-for","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","date":"2022-01-18","arxiv_id":"2201.06734","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-as-self-supervised","title":"Knowledge Distillation as Self-Supervised Learning","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moebert-from-bert-to-mixture-of-experts-via","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nearest-neighbor-knowledge-distillation-for","title":"Nearest Neighbor Knowledge Distillation for Neural Machine Translation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-knowledge-distillation-for-compressing","title":"Tree Knowledge Distillation for Compressing Transformer-Based Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"microdosing-knowledge-distillation-for-gan","title":"Microdosing: Knowledge Distillation for GAN based Compression","date":"2022-01-07","arxiv_id":"2201.02624","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-similarity-weighted-knowledge","title":"Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":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,"repositories_listed":0,"syntology":null},{"url":null,"slug":"image-restoration-using-feature-guidance","title":"Image Restoration using Feature-guidance","date":"2022-01-01","arxiv_id":"2201.00187","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-video-model-transfer-with-dynamic","title":"Improving Video Model Transfer With Dynamic Representation Learning","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-diverse-human-motion","title":"Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-aware-mutual-knowledge","title":"Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-generative-data-free-knowledge","title":"Conditional Generative Data-free Knowledge Distillation","date":"2021-12-31","arxiv_id":"2112.15358","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-knowledge-transfer-a-survey","title":"Data-Free Knowledge Transfer: A Survey","date":"2021-12-31","arxiv_id":"2112.15278","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-federated-distillation-learning","title":"An Efficient Federated Distillation Learning System for Multi-task Time Series Classification","date":"2021-12-30","arxiv_id":"2201.00011","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-mixed-precision-quantization-search","title":"Automatic Mixed-Precision Quantization Search of BERT","date":"2021-12-30","arxiv_id":"2112.14938","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-beam-search-to-enhance-on-device","title":"Adaptive Beam Search to Enhance On-device Abstractive Summarization","date":"2021-12-22","arxiv_id":"2201.02739","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-distillation-mixup-training-for-non","title":"Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation","date":"2021-12-22","arxiv_id":"2112.11640","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modality-distillation-via-learning-the","title":"Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix","date":"2021-12-21","arxiv_id":"2112.11447","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-graph-contrastive-pretraining-for","title":"Supervised Graph Contrastive Pretraining for Text Classification","date":"2021-12-21","arxiv_id":"2112.11389","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-the-quality-of-distillation-in","title":"Controlling the Quality of Distillation in Response-Based Network Compression","date":"2021-12-19","arxiv_id":"2112.10047","repositories_listed":0,"syntology":null},{"url":null,"slug":"legodnn-block-grained-scaling-of-deep-neural","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","date":"2021-12-18","arxiv_id":"2112.09852","repositories_listed":0,"syntology":null},{"url":null,"slug":"distill-and-de-bias-mitigating-bias-in-face","title":"Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation","date":"2021-12-17","arxiv_id":"2112.09786","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillation-of-human-object-interaction","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","date":"2021-12-17","arxiv_id":"2112.09448","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-improves-stability-in","title":"Knowledge Distillation Improves Stability in Retranslation-based Simultaneous Translation","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-semantic-segmentation-via","title":"Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching","date":"2021-12-17","arxiv_id":"2112.09459","repositories_listed":0,"syntology":null},{"url":null,"slug":"amortized-noisy-channel-neural-machine","title":"Amortized Noisy Channel Neural Machine Translation","date":"2021-12-16","arxiv_id":"2112.08670","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-unified-foundation-model-jointly","title":"Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text","date":"2021-12-14","arxiv_id":"2112.07074","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-unsupervised-domain-adaptive-person","title":"Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation","date":"2021-12-13","arxiv_id":"2112.06632","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-object-detection","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","date":"2021-12-09","arxiv_id":"2112.04840","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-adversarial-training-learning-together","title":"Mutual Adversarial Training: Learning together is better than going alone","date":"2021-12-09","arxiv_id":"2112.05005","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-contrastive-learning-with-relation","title":"Boosting Contrastive Learning with Relation Knowledge Distillation","date":"2021-12-08","arxiv_id":"2112.04174","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-knowledge-from-features-with","title":"Extracting knowledge from features with multilevel abstraction","date":"2021-12-04","arxiv_id":"2112.13642","repositories_listed":0,"syntology":null},{"url":null,"slug":"kdctime-knowledge-distillation-with","title":"KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-series Classification","date":"2021-12-04","arxiv_id":"2112.02291","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedrad-federated-robust-adaptive-distillation","title":"FedRAD: Federated Robust Adaptive Distillation","date":"2021-12-02","arxiv_id":"2112.01405","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-confidentiality-of","title":"Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"58b4b2f8058cb321ab2d0548e2de4b18c7afc64bd2b9800d1cfe2a01d3876933","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}