{"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/20","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":20,"pages_in_order":31,"rows_per_page":100,"rows":[1901,2000],"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/19","next":"/method/knowledge-distillation/papers/21","papers":[{"paper":null,"slug":"effectiveness-of-function-matching-in-driving","title":"Effectiveness of Function Matching in Driving Scene Recognition","date":"2022-08-20","arxiv_id":"2208.09694","n_code_links":0,"syntology":null},{"paper":"/paper/mind-the-gap-in-distilling-stylegans","slug":"mind-the-gap-in-distilling-stylegans","title":"Mind the Gap in Distilling StyleGANs","date":"2022-08-18","arxiv_id":"2208.08840","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-the-knowledge-in-a-dnn-to-explain","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","date":"2022-08-18","arxiv_id":"2208.08741","n_code_links":0,"syntology":null},{"paper":null,"slug":"progressive-cross-modal-knowledge","title":"Progressive Cross-modal Knowledge Distillation for Human Action Recognition","date":"2022-08-17","arxiv_id":"2208.08090","n_code_links":0,"syntology":null},{"paper":null,"slug":"rawtobit-a-fully-end-to-end-camera-isp","title":"RAWtoBit: A Fully End-to-end Camera ISP Network","date":"2022-08-16","arxiv_id":"2208.07639","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-domain-adaptation-for-2","title":"Unsupervised Domain Adaptation for Segmentation with Black-box Source Model","date":"2022-08-16","arxiv_id":"2208.07769","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-knowledge-distillation-based-backdoor","title":"A Knowledge Distillation-Based Backdoor Attack in Federated Learning","date":"2022-08-12","arxiv_id":"2208.06176","n_code_links":0,"syntology":null},{"paper":"/paper/beit-v2-masked-image-modeling-with-vector","slug":"beit-v2-masked-image-modeling-with-vector","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","date":"2022-08-12","arxiv_id":"2208.06366","n_code_links":3,"syntology":null},{"paper":null,"slug":"non-autoregressive-sign-language-production","title":"Non-Autoregressive Sign Language Production via Knowledge Distillation","date":"2022-08-12","arxiv_id":"2208.06183","n_code_links":0,"syntology":null},{"paper":"/paper/mixskd-self-knowledge-distillation-from-mixup","slug":"mixskd-self-knowledge-distillation-from-mixup","title":"MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition","date":"2022-08-11","arxiv_id":"2208.05768","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["winycg/self-kd-lib"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pa-seg-learning-from-point-annotations-for-3d","slug":"pa-seg-learning-from-point-annotations-for-3d","title":"PA-Seg: Learning from Point Annotations for 3D Medical Image Segmentation using Contextual Regularization and Cross Knowledge Distillation","date":"2022-08-11","arxiv_id":"2208.05669","n_code_links":1,"syntology":null},{"paper":"/paper/skdcgn-source-free-knowledge-distillation-of","slug":"skdcgn-source-free-knowledge-distillation-of","title":"SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs","date":"2022-08-08","arxiv_id":"2208.04226","n_code_links":1,"syntology":null},{"paper":null,"slug":"label-semantic-knowledge-distillation-for","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","date":"2022-08-07","arxiv_id":"2208.03763","n_code_links":0,"syntology":null},{"paper":null,"slug":"study-of-encoder-decoder-architectures-for","title":"Study of Encoder-Decoder Architectures for Code-Mix Search Query Translation","date":"2022-08-07","arxiv_id":"2208.03713","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-semi-supervised-and-self-supervised","title":"Deep Semi-Supervised and Self-Supervised Learning for Diabetic Retinopathy Detection","date":"2022-08-04","arxiv_id":"2208.02408","n_code_links":0,"syntology":null},{"paper":"/paper/distributional-correlation-aware-knowledge","slug":"distributional-correlation-aware-knowledge","title":"Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction","date":"2022-08-04","arxiv_id":"2208.07232","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["lancopku/dckd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/kd-scfnet-towards-more-accurate-and-efficient","slug":"kd-scfnet-towards-more-accurate-and-efficient","title":"KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation","date":"2022-08-03","arxiv_id":"2208.02178","n_code_links":1,"syntology":null},{"paper":null,"slug":"pose-uncertainty-aware-movement-synchrony","title":"Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer","date":"2022-08-01","arxiv_id":"2208.01161","n_code_links":0,"syntology":null},{"paper":"/paper/aggretriever-a-simple-approach-to-aggregate","slug":"aggretriever-a-simple-approach-to-aggregate","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","date":"2022-07-31","arxiv_id":"2208.00511","n_code_links":1,"syntology":null},{"paper":"/paper/chinese-grammatical-error-correction-based-on-1","slug":"chinese-grammatical-error-correction-based-on-1","title":"Chinese grammatical error correction based on knowledge distillation","date":"2022-07-31","arxiv_id":"2208.00351","n_code_links":2,"syntology":null},{"paper":"/paper/meta-learning-based-degradation","slug":"meta-learning-based-degradation","title":"Meta-Learning based Degradation Representation for Blind Super-Resolution","date":"2022-07-28","arxiv_id":"2207.13963","n_code_links":1,"syntology":null},{"paper":null,"slug":"sdbert-sparsedistilbert-a-faster-and-smaller","title":"SDBERT: SparseDistilBERT, a faster and smaller BERT model","date":"2022-07-28","arxiv_id":"2208.10246","n_code_links":0,"syntology":null},{"paper":null,"slug":"nicest-noisy-label-correction-and-training","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","date":"2022-07-27","arxiv_id":"2207.13316","n_code_links":0,"syntology":null},{"paper":"/paper/robust-and-efficient-segmentation-of-cross","slug":"robust-and-efficient-segmentation-of-cross","title":"Exploring Generalizable Distillation for Efficient Medical Image Segmentation","date":"2022-07-26","arxiv_id":"2207.12995","n_code_links":1,"syntology":null},{"paper":"/paper/domain-invariant-feature-exploration-for","slug":"domain-invariant-feature-exploration-for","title":"Domain-invariant Feature Exploration for Domain Generalization","date":"2022-07-25","arxiv_id":"2207.12020","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jindongwang/transferlearning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"few-shot-object-detection-by-knowledge","title":"Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations","date":"2022-07-25","arxiv_id":"2207.12049","n_code_links":0,"syntology":null},{"paper":null,"slug":"hire-distilling-high-order-relational","title":"HIRE: Distilling High-order Relational Knowledge From Heterogeneous Graph Neural Networks","date":"2022-07-25","arxiv_id":"2207.11887","n_code_links":0,"syntology":null},{"paper":"/paper/handling-data-heterogeneity-in-federated","slug":"handling-data-heterogeneity-in-federated","title":"Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion","date":"2022-07-23","arxiv_id":"2207.11447","n_code_links":1,"syntology":null},{"paper":"/paper/online-knowledge-distillation-via-mutual","slug":"online-knowledge-distillation-via-mutual","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","date":"2022-07-23","arxiv_id":"2207.11518","n_code_links":2,"syntology":null},{"paper":"/paper/spatial-channel-token-distillation-for-vision","slug":"spatial-channel-token-distillation-for-vision","title":"Spatial-Channel Token Distillation for Vision MLPs","date":"2022-07-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-class-incremental-learning-via-1","slug":"few-shot-class-incremental-learning-via-1","title":"Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay","date":"2022-07-22","arxiv_id":"2207.11213","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["liuh127/FSCIL-via-Entropy-regularized-DF-Replay"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"federated-semi-supervised-domain-adaptation","title":"Federated Semi-Supervised Domain Adaptation via Knowledge Transfer","date":"2022-07-21","arxiv_id":"2207.10727","n_code_links":0,"syntology":null},{"paper":null,"slug":"many-to-one-knowledge-distillation-of-real","title":"Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems","date":"2022-07-20","arxiv_id":"2208.00885","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-compression-for-resource-constrained","title":"Model Compression for Resource-Constrained Mobile Robots","date":"2022-07-20","arxiv_id":"2207.10082","n_code_links":0,"syntology":null},{"paper":"/paper/context-unaware-knowledge-distillation-for","slug":"context-unaware-knowledge-distillation-for","title":"Context Unaware Knowledge Distillation for Image Retrieval","date":"2022-07-19","arxiv_id":"2207.09070","n_code_links":1,"syntology":null},{"paper":"/paper/fedx-unsupervised-federated-learning-with","slug":"fedx-unsupervised-federated-learning-with","title":"FedX: Unsupervised Federated Learning with Cross Knowledge Distillation","date":"2022-07-19","arxiv_id":"2207.09158","n_code_links":1,"syntology":null},{"paper":"/paper/informative-knowledge-distillation-for-image","slug":"informative-knowledge-distillation-for-image","title":"Informative knowledge distillation for image anomaly segmentation","date":"2022-07-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-knowledge-representation-with-meta","title":"Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution","date":"2022-07-18","arxiv_id":"2207.08356","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-data-augmentation-for-robust","slug":"rethinking-data-augmentation-for-robust","title":"Rethinking Data Augmentation for Robust Visual Question Answering","date":"2022-07-18","arxiv_id":"2207.08739","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":["itemzheng/kddaug"],"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":"subclass-knowledge-distillation-with-known","title":"Subclass Knowledge Distillation with Known Subclass Labels","date":"2022-07-17","arxiv_id":"2207.08063","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-versus-wide-an-analysis-of-student","title":"Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models","date":"2022-07-14","arxiv_id":"2207.06867","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-low-resolution-distillation-for-cost","slug":"dynamic-low-resolution-distillation-for-cost","title":"Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting","date":"2022-07-14","arxiv_id":"2207.06694","n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-knowledge-distillation-with","slug":"large-scale-knowledge-distillation-with","title":"Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources","date":"2022-07-14","arxiv_id":"2207.06667","n_code_links":1,"syntology":null},{"paper":null,"slug":"dspnet-towards-slimmable-pretrained-networks","title":"DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning","date":"2022-07-13","arxiv_id":"2207.06075","n_code_links":0,"syntology":null},{"paper":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"slimseg-slimmable-semantic-segmentation-with","title":"SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision","date":"2022-07-13","arxiv_id":"2207.06242","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-knowledge-distillation","title":"Cross-Architecture Knowledge Distillation","date":"2022-07-12","arxiv_id":"2207.05273","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-non-semantic-speech-embeddings-with","slug":"distilled-non-semantic-speech-embeddings-with","title":"Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices","date":"2022-07-12","arxiv_id":"2207.05784","n_code_links":1,"syntology":null},{"paper":"/paper/head-hetero-assists-distillation-for","slug":"head-hetero-assists-distillation-for","title":"HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors","date":"2022-07-12","arxiv_id":"2207.05345","n_code_links":1,"syntology":null},{"paper":null,"slug":"normalized-feature-distillation-for-semantic","title":"Normalized Feature Distillation for Semantic Segmentation","date":"2022-07-12","arxiv_id":"2207.05256","n_code_links":0,"syntology":null},{"paper":null,"slug":"1st-place-solution-to-the-epic-kitchens","title":"1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022","date":"2022-07-10","arxiv_id":"2207.05730","n_code_links":0,"syntology":null},{"paper":"/paper/2dpass-2d-priors-assisted-semantic","slug":"2dpass-2d-priors-assisted-semantic","title":"2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds","date":"2022-07-10","arxiv_id":"2207.04397","n_code_links":1,"syntology":null},{"paper":"/paper/fairdistillation-mitigating-stereotyping-in","slug":"fairdistillation-mitigating-stereotyping-in","title":"FairDistillation: Mitigating Stereotyping in Language Models","date":"2022-07-10","arxiv_id":"2207.04546","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-streaming-end-to-end-asr-on","title":"Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies","date":"2022-07-06","arxiv_id":"2207.02495","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-low-footprint-wake-word","title":"Low-resource Low-footprint Wake-word Detection using Knowledge Distillation","date":"2022-07-06","arxiv_id":"2207.03331","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generative-framework-for-personalized","title":"A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy","date":"2022-07-05","arxiv_id":"2207.01771","n_code_links":0,"syntology":null},{"paper":"/paper/act-net-asymmetric-co-teacher-network-for","slug":"act-net-asymmetric-co-teacher-network-for","title":"ACT-Net: Asymmetric Co-Teacher Network for Semi-supervised Memory-efficient Medical Image Segmentation","date":"2022-07-05","arxiv_id":"2207.01900","n_code_links":1,"syntology":null},{"paper":null,"slug":"glance-global-to-local-architecture-neutral","title":"GLANCE: Global to Local Architecture-Neutral Concept-based Explanations","date":"2022-07-05","arxiv_id":"2207.01917","n_code_links":0,"syntology":null},{"paper":"/paper/open-vocabulary-multi-label-classification","slug":"open-vocabulary-multi-label-classification","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","date":"2022-07-05","arxiv_id":"2207.01887","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sunanhe/mkt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vem-2-l-a-plug-and-play-framework-for-fusing","title":"VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion","date":"2022-07-04","arxiv_id":"2207.01528","n_code_links":0,"syntology":null},{"paper":"/paper/prue-distilling-knowledge-from-sparse-teacher","slug":"prue-distilling-knowledge-from-sparse-teacher","title":"PrUE: Distilling Knowledge from Sparse Teacher Networks","date":"2022-07-03","arxiv_id":"2207.00586","n_code_links":1,"syntology":null},{"paper":null,"slug":"listbert-learning-to-rank-e-commerce-products","title":"ListBERT: Learning to Rank E-commerce products with Listwise BERT","date":"2022-06-30","arxiv_id":"2206.15198","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-compression-of-sentence-transformer","title":"Extreme compression of sentence-transformer ranker models: faster inference, longer battery life, and less storage on edge devices","date":"2022-06-29","arxiv_id":"2207.12852","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-of-transformer-based","title":"Knowledge Distillation of Transformer-based Language Models Revisited","date":"2022-06-29","arxiv_id":"2206.14366","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-label-smoothing-and-knowledge","slug":"revisiting-label-smoothing-and-knowledge","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","date":"2022-06-29","arxiv_id":"2206.14532","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":9,"n_instrument":1,"unverified":6,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["sutd-visual-computing-group/LS-KD-compatibility"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/cooperative-retriever-and-ranker-in-deep","slug":"cooperative-retriever-and-ranker-in-deep","title":"Cooperative Retriever and Ranker in Deep Recommenders","date":"2022-06-28","arxiv_id":"2206.14649","n_code_links":1,"syntology":null},{"paper":null,"slug":"qti-submission-to-dcase-2021-residual","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","date":"2022-06-28","arxiv_id":"2206.13909","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-with-representative","title":"Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification","date":"2022-06-26","arxiv_id":"2206.12788","n_code_links":0,"syntology":null},{"paper":"/paper/feature-representation-learning-for-robust","slug":"feature-representation-learning-for-robust","title":"Feature Representation Learning for Robust Retinal Disease Detection from Optical Coherence Tomography Images","date":"2022-06-24","arxiv_id":"2206.12136","n_code_links":1,"syntology":null},{"paper":null,"slug":"online-distillation-with-mixed-sample","title":"Mixed Sample Augmentation for Online Distillation","date":"2022-06-24","arxiv_id":"2206.12370","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-via-weighted-ensemble","title":"Knowledge Distillation via Weighted Ensemble of Teaching Assistants","date":"2022-06-23","arxiv_id":"2206.12005","n_code_links":0,"syntology":null},{"paper":null,"slug":"conformer-with-dual-mode-chunked-attention","title":"Conformer with dual-mode chunked attention for joint online and offline ASR","date":"2022-06-22","arxiv_id":"2206.11157","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-oriented-object","title":"Knowledge Distillation for Oriented Object Detection on Aerial Images","date":"2022-06-20","arxiv_id":"2206.09796","n_code_links":0,"syntology":null},{"paper":"/paper/metafed-federated-learning-among-federations","slug":"metafed-federated-learning-among-federations","title":"MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare","date":"2022-06-17","arxiv_id":"2206.08516","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-scale-feature-extraction-and-fusion-for","title":"Multi scale Feature Extraction and Fusion for Online Knowledge Distillation","date":"2022-06-16","arxiv_id":"2206.08224","n_code_links":0,"syntology":null},{"paper":null,"slug":"freekd-free-direction-knowledge-distillation","title":"FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks","date":"2022-06-14","arxiv_id":"2206.06561","n_code_links":0,"syntology":null},{"paper":null,"slug":"freetransfer-x-safe-and-label-free-cross","title":"FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models","date":"2022-06-14","arxiv_id":"2206.06586","n_code_links":0,"syntology":null},{"paper":null,"slug":"soteacher-a-student-oriented-teacher-network","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","date":"2022-06-14","arxiv_id":"2206.06661","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-bayesian-neural-regression-a","title":"Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process","date":"2022-06-13","arxiv_id":"2206.06357","n_code_links":0,"syntology":null},{"paper":"/paper/the-modality-focusing-hypothesis-on-the-blink","slug":"the-modality-focusing-hypothesis-on-the-blink","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","date":"2022-06-13","arxiv_id":"2206.06487","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":["zihuixue/mfh"],"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/reducing-capacity-gap-in-knowledge","slug":"reducing-capacity-gap-in-knowledge","title":"Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting","date":"2022-06-11","arxiv_id":"2206.05475","n_code_links":1,"syntology":null},{"paper":null,"slug":"distillation-decision-tree","title":"Knowledge Distillation Decision Tree for Unravelling Black-box Machine Learning Models","date":"2022-06-09","arxiv_id":"2206.04661","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrowing-the-coordinate-frame-gap-in","title":"Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting","date":"2022-06-08","arxiv_id":"2206.03970","n_code_links":0,"syntology":null},{"paper":"/paper/cvil-cross-lingual-training-of-vision","slug":"cvil-cross-lingual-training-of-vision","title":"cViL: Cross-Lingual Training of Vision-Language Models using Knowledge Distillation","date":"2022-06-07","arxiv_id":"2206.03354","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-knowledge-graph-embedding-via","title":"Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding","date":"2022-06-07","arxiv_id":"2206.02963","n_code_links":0,"syntology":null},{"paper":null,"slug":"lip-listening-mixing-senses-to-understand","title":"Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based Models","date":"2022-06-05","arxiv_id":"2207.05692","n_code_links":0,"syntology":null},{"paper":"/paper/point-to-voxel-knowledge-distillation-for-1","slug":"point-to-voxel-knowledge-distillation-for-1","title":"Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation","date":"2022-06-05","arxiv_id":"2206.02099","n_code_links":0,"syntology":null},{"paper":null,"slug":"vanilla-feature-distillation-for-improving","title":"Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training","date":"2022-06-05","arxiv_id":"2206.02158","n_code_links":0,"syntology":null},{"paper":"/paper/extreme-compression-for-pre-trained","slug":"extreme-compression-for-pre-trained","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","date":"2022-06-04","arxiv_id":"2206.01859","n_code_links":1,"syntology":null},{"paper":null,"slug":"guided-deep-metric-learning","title":"Guided Deep Metric Learning","date":"2022-06-04","arxiv_id":"2206.02029","n_code_links":0,"syntology":null},{"paper":"/paper/zeroquant-efficient-and-affordable-post","slug":"zeroquant-efficient-and-affordable-post","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","date":"2022-06-04","arxiv_id":"2206.01861","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/DeepSpeed"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"3d-augmented-contrastive-knowledge","title":"3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation","date":"2022-06-02","arxiv_id":"2206.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generalized-supervised-contrastive-learning","title":"Generalized Supervised Contrastive Learning","date":"2022-06-01","arxiv_id":"2206.00384","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-cross-silo-advertising-with","slug":"semi-supervised-cross-silo-advertising-with","title":"VFed-SSD: Towards Practical Vertical Federated Advertising","date":"2022-05-31","arxiv_id":"2205.15987","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-spectral-representations-for","title":"Spectral Maps for Learning on Subgraphs","date":"2022-05-30","arxiv_id":"2205.14938","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-6d-pose-estimation","title":"Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions","date":"2022-05-30","arxiv_id":"2205.14971","n_code_links":0,"syntology":null},{"paper":"/paper/rlx2-training-a-sparse-deep-reinforcement","slug":"rlx2-training-a-sparse-deep-reinforcement","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","date":"2022-05-30","arxiv_id":"2205.15043","n_code_links":1,"syntology":null},{"paper":"/paper/towards-efficient-3d-object-detection-with","slug":"towards-efficient-3d-object-detection-with","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","date":"2022-05-30","arxiv_id":"2205.15156","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["cvmi-lab/sparsekd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"a-general-multiple-data-augmentation-based","title":"A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks","date":"2022-05-29","arxiv_id":"2205.14606","n_code_links":0,"syntology":null},{"paper":"/paper/autodisc-automatic-distillation-schedule-for","slug":"autodisc-automatic-distillation-schedule-for","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","date":"2022-05-29","arxiv_id":"2205.14570","n_code_links":1,"syntology":null}],"record_sha256":"f864b5e45e1aad6e63c4f64814a3360c6f7477b3e6323fdc5f52a2522995dc54","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}