{"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/17","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":17,"pages_in_order":31,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/method/knowledge-distillation/papers/18","papers":[{"paper":null,"slug":"a-knowledge-distillation-framework-for-multi","title":"A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image","date":"2023-02-24","arxiv_id":"2302.12562","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensemble-knowledge-distillation-of-self","title":"Ensemble knowledge distillation of self-supervised speech models","date":"2023-02-24","arxiv_id":"2302.12757","n_code_links":0,"syntology":null},{"paper":"/paper/a-framework-for-benchmarking-class-out-of-1","slug":"a-framework-for-benchmarking-class-out-of-1","title":"A framework for benchmarking class-out-of-distribution detection and its application to ImageNet","date":"2023-02-23","arxiv_id":"2302.11893","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mdabbah/COOD_benchmarking"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-neural-span-based-continual-named-entity","slug":"a-neural-span-based-continual-named-entity","title":"A Neural Span-Based Continual Named Entity Recognition Model","date":"2023-02-23","arxiv_id":"2302.12200","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["qznan/spankl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"personalized-decentralized-federated-learning","title":"Personalized Decentralized Federated Learning with Knowledge Distillation","date":"2023-02-23","arxiv_id":"2302.12156","n_code_links":0,"syntology":null},{"paper":"/paper/teacher-intervention-improving-convergence-of","slug":"teacher-intervention-improving-convergence-of","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","date":"2023-02-23","arxiv_id":"2302.11812","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":["marsjacobs/ti-kd-qat"],"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":["unlocated"]}}},{"paper":"/paper/cekd-cross-modal-edge-privileged-knowledge","slug":"cekd-cross-modal-edge-privileged-knowledge","title":"CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images","date":"2023-02-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"debiased-distillation-by-transplanting-the","title":"Debiased Distillation by Transplanting the Last Layer","date":"2023-02-22","arxiv_id":"2302.11187","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-calibrated-student-from-an","title":"Distilling Calibrated Student from an Uncalibrated Teacher","date":"2023-02-22","arxiv_id":"2302.11472","n_code_links":0,"syntology":null},{"paper":"/paper/ks-detr-knowledge-sharing-in-attention","slug":"ks-detr-knowledge-sharing-in-attention","title":"KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer","date":"2023-02-22","arxiv_id":"2302.11208","n_code_links":1,"syntology":null},{"paper":null,"slug":"two-in-one-knowledge-distillation-for","title":"Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection","date":"2023-02-21","arxiv_id":"2302.10437","n_code_links":0,"syntology":null},{"paper":"/paper/social4rec-distilling-user-preference-from","slug":"social4rec-distilling-user-preference-from","title":"Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in Tencent","date":"2023-02-20","arxiv_id":"2302.09971","n_code_links":2,"syntology":null},{"paper":null,"slug":"fairly-predicting-graft-failure-in-liver","title":"Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning","date":"2023-02-18","arxiv_id":"2302.09400","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustdistiller-compressing-universal-speech","title":"RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness","date":"2023-02-18","arxiv_id":"2302.09437","n_code_links":0,"syntology":null},{"paper":null,"slug":"explicit-and-implicit-knowledge-distillation","title":"Explicit and Implicit Knowledge Distillation via Unlabeled Data","date":"2023-02-17","arxiv_id":"2302.08771","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-3d-lidar-semantic-segmentation-for","title":"Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving","date":"2023-02-17","arxiv_id":"2302.08785","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modal-distillation-for-flood-extent","title":"Cross Modal Distillation for Flood Extent Mapping","date":"2023-02-16","arxiv_id":"2302.08180","n_code_links":0,"syntology":null},{"paper":null,"slug":"fuzzy-knowledge-distillation-from-high-order","title":"Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK","date":"2023-02-16","arxiv_id":"2302.08038","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-biased-soft-labels","title":"Learning From Biased Soft Labels","date":"2023-02-16","arxiv_id":"2302.08155","n_code_links":0,"syntology":null},{"paper":"/paper/st-mfnet-mini-knowledge-distillation-driven","slug":"st-mfnet-mini-knowledge-distillation-driven","title":"ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation","date":"2023-02-16","arxiv_id":"2302.08455","n_code_links":1,"syntology":null},{"paper":null,"slug":"offline-to-online-knowledge-distillation-for","title":"Offline-to-Online Knowledge Distillation for Video Instance Segmentation","date":"2023-02-15","arxiv_id":"2302.07516","n_code_links":0,"syntology":null},{"paper":"/paper/multi-teacher-knowledge-distillation-as-an","slug":"multi-teacher-knowledge-distillation-as-an","title":"Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networks","date":"2023-02-14","arxiv_id":"2302.07215","n_code_links":2,"syntology":null},{"paper":null,"slug":"take-a-prior-from-other-tasks-for-severe-blur","title":"Take a Prior from Other Tasks for Severe Blur Removal","date":"2023-02-14","arxiv_id":"2302.06898","n_code_links":0,"syntology":null},{"paper":"/paper/cholectriplet2022-show-me-a-tool-and-tell-me","slug":"cholectriplet2022-show-me-a-tool-and-tell-me","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","date":"2023-02-13","arxiv_id":"2302.06294","n_code_links":2,"syntology":null},{"paper":"/paper/learning-from-noisy-crowd-labels-with-logics","slug":"learning-from-noisy-crowd-labels-with-logics","title":"Learning from Noisy Crowd Labels with Logics","date":"2023-02-13","arxiv_id":"2302.06337","n_code_links":1,"syntology":null},{"paper":"/paper/perada-parameter-efficient-and-generalizable","slug":"perada-parameter-efficient-and-generalizable","title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","date":"2023-02-13","arxiv_id":"2302.06637","n_code_links":1,"syntology":null},{"paper":null,"slug":"sclifd-supervised-contrastive-knowledge","title":"SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data","date":"2023-02-12","arxiv_id":"2302.05929","n_code_links":0,"syntology":null},{"paper":"/paper/dual-relation-knowledge-distillation-for","slug":"dual-relation-knowledge-distillation-for","title":"Dual Relation Knowledge Distillation for Object Detection","date":"2023-02-11","arxiv_id":"2302.05637","n_code_links":1,"syntology":null},{"paper":"/paper/jaccard-metric-losses-optimizing-the-jaccard-1","slug":"jaccard-metric-losses-optimizing-the-jaccard-1","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","date":"2023-02-11","arxiv_id":"2302.05666","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["zifuwanggg/jdtlosses"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-affinity-assisted-knowledge","title":"Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data","date":"2023-02-10","arxiv_id":"2302.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-text-based-human-search-and-approach","title":"SOCRATES: Text-based Human Search and Approach using a Robot Dog","date":"2023-02-10","arxiv_id":"2302.05324","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-transformers-for-clinical-natural","slug":"lightweight-transformers-for-clinical-natural","title":"Lightweight Transformers for Clinical Natural Language Processing","date":"2023-02-09","arxiv_id":"2302.04725","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-modality-agnostic-representations","title":"Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation","date":"2023-02-08","arxiv_id":"2302.04308","n_code_links":0,"syntology":null},{"paper":null,"slug":"slam-student-label-mixing-for-semi-supervised","title":"SLaM: Student-Label Mixing for Distillation with Unlabeled Examples","date":"2023-02-08","arxiv_id":"2302.03806","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-representation-learning-by-distilling","title":"Audio Representation Learning by Distilling Video as Privileged Information","date":"2023-02-06","arxiv_id":"2302.02845","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-federated-knowledge-graph","title":"Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning","date":"2023-02-04","arxiv_id":"2302.02069","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-in-vision-transformers","title":"Knowledge Distillation in Vision Transformers: A Critical Review","date":"2023-02-04","arxiv_id":"2302.02108","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-once-for-all-a-study-on-parallel","title":"Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits","date":"2023-02-03","arxiv_id":"2302.01888","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-search-and-training-for-robust-and","slug":"adaptive-search-and-training-for-robust-and","title":"Adaptive Search-and-Training for Robust and Efficient Network Pruning","date":"2023-02-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/distill-dbdgan-knowledge-distillation-and","slug":"distill-dbdgan-knowledge-distillation-and","title":"Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur Detection","date":"2023-02-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-knowledge-distillation-for-pre","title":"Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection","date":"2023-02-01","arxiv_id":"2302.00444","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-on-graphs-a-survey","title":"Knowledge Distillation on Graphs: A Survey","date":"2023-02-01","arxiv_id":"2302.00219","n_code_links":0,"syntology":null},{"paper":null,"slug":"amd-adaptive-masked-distillation-for-object","title":"AMD: Adaptive Masked Distillation for Object Detection","date":"2023-01-31","arxiv_id":"2301.13538","n_code_links":0,"syntology":null},{"paper":"/paper/fractalad-a-simple-industrial-anomaly","slug":"fractalad-a-simple-industrial-anomaly","title":"FractalAD: A simple industrial anomaly detection method using fractal anomaly generation and backbone knowledge distillation","date":"2023-01-30","arxiv_id":"2301.12739","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-approx-label-smoothing","title":"Knowledge Distillation $\\approx$ Label Smoothing: Fact or Fallacy?","date":"2023-01-30","arxiv_id":"2301.12609","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-transfer-from-pre-trained-language","slug":"knowledge-transfer-from-pre-trained-language","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","date":"2023-01-30","arxiv_id":"2301.13003","n_code_links":2,"syntology":null},{"paper":null,"slug":"few-shot-face-image-translation-via-gan-prior","title":"Few-shot Face Image Translation via GAN Prior Distillation","date":"2023-01-28","arxiv_id":"2301.12257","n_code_links":0,"syntology":null},{"paper":null,"slug":"mvkt-ecg-efficient-single-lead-ecg","title":"MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring","date":"2023-01-28","arxiv_id":"2301.12178","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-we-use-probing-to-better-understand-fine","title":"Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?","date":"2023-01-27","arxiv_id":"2301.11688","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-simple-recipe-for-competitive-low-compute","title":"A Simple Recipe for Competitive Low-compute Self supervised Vision Models","date":"2023-01-23","arxiv_id":"2301.09451","n_code_links":0,"syntology":null},{"paper":"/paper/unifying-synergies-between-self-supervised","slug":"unifying-synergies-between-self-supervised","title":"Unifying Synergies between Self-supervised Learning and Dynamic Computation","date":"2023-01-22","arxiv_id":"2301.09164","n_code_links":1,"syntology":null},{"paper":null,"slug":"prokd-an-unsupervised-prototypical-knowledge","title":"ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition","date":"2023-01-21","arxiv_id":"2301.08855","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-best-of-both-worlds-accurate-global-and","title":"The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation","date":"2023-01-21","arxiv_id":"2301.08968","n_code_links":0,"syntology":null},{"paper":null,"slug":"rnas-cl-robust-neural-architecture-search-by","title":"RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation","date":"2023-01-19","arxiv_id":"2301.08092","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptively-integrated-knowledge-distillation","title":"Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning","date":"2023-01-18","arxiv_id":"2301.07316","n_code_links":0,"syntology":null},{"paper":"/paper/survey-of-knowledge-distillation-in-federated","slug":"survey-of-knowledge-distillation-in-federated","title":"Knowledge Distillation in Federated Edge Learning: A Survey","date":"2023-01-14","arxiv_id":"2301.05849","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-cohesive-distillation-architecture-for","title":"A Cohesive Distillation Architecture for Neural Language Models","date":"2023-01-12","arxiv_id":"2301.08130","n_code_links":0,"syntology":null},{"paper":"/paper/clip2scene-towards-label-efficient-3d-scene","slug":"clip2scene-towards-label-efficient-3d-scene","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","date":"2023-01-12","arxiv_id":"2301.04926","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-decision-boundary-learning-for","title":"Effective Decision Boundary Learning for Class Incremental Learning","date":"2023-01-12","arxiv_id":"2301.05180","n_code_links":0,"syntology":null},{"paper":"/paper/online-hyperparameter-optimization-for-class","slug":"online-hyperparameter-optimization-for-class","title":"Online Hyperparameter Optimization for Class-Incremental Learning","date":"2023-01-11","arxiv_id":"2301.05032","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["yaoyao-liu/online-hyperparameter-optimization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/synthetic-data-generation-method-for-data","slug":"synthetic-data-generation-method-for-data","title":"Synthetic data generation method for data-free knowledge distillation in regression neural networks","date":"2023-01-11","arxiv_id":"2301.04338","n_code_links":1,"syntology":null},{"paper":"/paper/ernie-3-0-tiny-frustratingly-simple-method-to","slug":"ernie-3-0-tiny-frustratingly-simple-method-to","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","date":"2023-01-09","arxiv_id":"2301.03416","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":["PaddlePaddle/PaddleNLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"designing-an-improved-deep-learning-based","title":"Designing an Improved Deep Learning-based Model for COVID-19 Recognition in Chest X-ray Images: A Knowledge Distillation Approach","date":"2023-01-06","arxiv_id":"2301.02735","n_code_links":0,"syntology":null},{"paper":"/paper/further-improving-weakly-supervised-object","slug":"further-improving-weakly-supervised-object","title":"Knowledge-guided Causal Intervention for Weakly-supervised Object Localization","date":"2023-01-03","arxiv_id":"2301.01060","n_code_links":1,"syntology":null},{"paper":"/paper/reliant-fair-knowledge-distillation-for-graph","slug":"reliant-fair-knowledge-distillation-for-graph","title":"RELIANT: Fair Knowledge Distillation for Graph Neural Networks","date":"2023-01-03","arxiv_id":"2301.01150","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":{"repos":["yushundong/reliant"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"automated-knowledge-distillation-via-monte","title":"Automated Knowledge Distillation via Monte Carlo Tree Search","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/beyond-the-limitation-of-monocular-3d","slug":"beyond-the-limitation-of-monocular-3d","title":"Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bilateral-memory-consolidation-for-continual","title":"Bilateral Memory Consolidation for Continual Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/boosting-accuracy-and-robustness-of-student","slug":"boosting-accuracy-and-robustness-of-student","title":"Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/capride-learning-confidential-and-private","slug":"capride-learning-confidential-and-private","title":"CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"clipping-distilling-clip-based-models-with-a","title":"CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/data-free-class-incremental-hand-gesture","slug":"data-free-class-incremental-hand-gesture","title":"Data-Free Class-Incremental Hand Gesture Recognition","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/data-free-knowledge-distillation-via-feature","slug":"data-free-knowledge-distillation-via-feature","title":"Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/distilling-cross-temporal-contexts-for","slug":"distilling-cross-temporal-contexts-for","title":"Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/distilling-detr-with-visual-linguistic","slug":"distilling-detr-with-visual-linguistic","title":"Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-focal-knowledge-from-imperfect","title":"Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-learning-with-dynamic-knowledge","slug":"dual-learning-with-dynamic-knowledge","title":"Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fedict-federated-multi-task-distillation-for","slug":"fedict-federated-multi-task-distillation-for","title":"FedICT: Federated Multi-task Distillation for Multi-access Edge Computing","date":"2023-01-01","arxiv_id":"2301.00389","n_code_links":1,"syntology":null},{"paper":null,"slug":"icd-face-intra-class-compactness-distillation","title":"ICD-Face: Intra-class Compactness Distillation for Face Recognition","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"incrementer-transformer-for-class-incremental","title":"Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-spreader-learning-semi-supervised","title":"Knowledge-Spreader: Learning Semi-Supervised Facial Action Dynamics by Consistifying Knowledge Granularity","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/label-guided-knowledge-distillation-for","slug":"label-guided-knowledge-distillation-for","title":"Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"masked-autoencoders-are-stronger-knowledge","title":"Masked Autoencoders Are Stronger Knowledge Distillers","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-level-logit-distillation","slug":"multi-level-logit-distillation","title":"Multi-Level Logit Distillation","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-knowledge","title":"Multi-Task Learning with Knowledge Distillation for Dense Prediction","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"open-set-fine-grained-retrieval-via-prompting","title":"Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-knowledge-distillation-of-face","title":"Probabilistic Knowledge Distillation of Face Ensembles","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/remembering-normality-memory-guided-knowledge","slug":"remembering-normality-memory-guided-knowledge","title":"Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/revisiting-prototypical-network-for-cross","slug":"revisiting-prototypical-network-for-cross","title":"Revisiting Prototypical Network for Cross Domain Few-Shot Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"scalekd-distilling-scale-aware-knowledge-in","title":"ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"smoc-net-leveraging-camera-pose-for-self","title":"SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tiny-updater-towards-efficient-neural-network","title":"Tiny Updater: Towards Efficient Neural Network-Driven Software Updating","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"triple-revisiting-pretrained-model-reuse-and","title":"TripLe: Revisiting Pretrained Model Reuse and Progressive Learning for Efficient Vision Transformer Scaling and Searching","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unikd-universal-knowledge-distillation-for","title":"UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/x3kd-knowledge-distillation-across-modalities","slug":"x3kd-knowledge-distillation-across-modalities","title":"X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-unified-object-counting-network-with-object","slug":"a-unified-object-counting-network-with-object","title":"A Unified Object Counting Network with Object Occupation Prior","date":"2022-12-29","arxiv_id":"2212.14193","n_code_links":1,"syntology":null},{"paper":"/paper/discriminator-cooperated-feature-map","slug":"discriminator-cooperated-feature-map","title":"Discriminator-Cooperated Feature Map Distillation for GAN Compression","date":"2022-12-29","arxiv_id":"2212.14169","n_code_links":1,"syntology":null},{"paper":"/paper/resolving-task-confusion-in-dynamic-expansion","slug":"resolving-task-confusion-in-dynamic-expansion","title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","date":"2022-12-29","arxiv_id":"2212.14284","n_code_links":1,"syntology":null},{"paper":"/paper/nern-learning-neural-representations-for","slug":"nern-learning-neural-representations-for","title":"NeRN -- Learning Neural Representations for Neural Networks","date":"2022-12-27","arxiv_id":"2212.13554","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["maorash/nern"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/prototype-guided-cross-task-knowledge","slug":"prototype-guided-cross-task-knowledge","title":"Prototype-guided Cross-task Knowledge Distillation for Large-scale Models","date":"2022-12-26","arxiv_id":"2212.13180","n_code_links":1,"syntology":null}],"record_sha256":"5d210171f65f1021650b9a788e3a350122c31920aa3859cb1ae89e74067db9f4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}