{"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/37","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":37,"pages_in_order":43,"rows_per_page":100,"rows":[3601,3700],"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/36","next":"/task/knowledge-distillation/papers/38","papers":[{"url":null,"slug":"a-unified-knowledge-distillation-framework","title":"A Unified Knowledge Distillation Framework for Deep Directed Graphical Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-label-smoothing-with-self-knowledge","title":"Adaptive Label Smoothing with Self-Knowledge","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-channel-pruning-with-learned","title":"Automated Channel Pruning with Learned Importance","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-compression","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","date":"2021-09-29","arxiv_id":"2109.14710","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-gans-with-style-mixed-triplets-for","title":"Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-knowledge-graph-embedding-via","title":"Explaining Knowledge Graph Embedding via Latent Rule Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-knowledge-distillation-for-few","title":"Exploiting Knowledge Distillation for Few-Shot Image Generation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-efficient-once-for-all-networks-for","title":"Fast and Efficient Once-For-All Networks for Diverse Hardware Deployment","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-kernel-distillation","title":"Feature Kernel Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-annotate-and-learn-generative-models-1","title":"Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-image-super-resolution","title":"Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moba-multi-teacher-model-based-reinforcement","title":"MOBA: Multi-teacher Model Based Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-via-ensemble-based","title":"Neural Architecture Search via Ensemble-based Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"not-all-regions-are-worthy-to-be-distilled","title":"Not All Regions are Worthy to be Distilled: Region-aware Knowledge Distillation Towards Efficient Image-to-Image Translation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prototypical-contrastive-predictive-coding","title":"Prototypical Contrastive Predictive Coding","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-knowledge-distillation-towards","title":"Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-the-teacher-student-gap-via-adaptive","title":"Reducing the Teacher-Student Gap via Adaptive Temperatures","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-consolidation-from-multiple","title":"Representation Consolidation from Multiple Expert Teachers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-fair-learning-to-hundreds-of","title":"Scaling Fair Learning to Hundreds of Intersectional Groups","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-distilled-pruning-of-neural-networks","title":"Self-Distilled Pruning Of Neural Networks","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-slimming-vision-transformer","title":"Self-Slimming Vision Transformer","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-models-are-good-teaching","title":"Self-supervised Models are Good Teaching Assistants for Vision Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"source-target-unified-knowledge-distillation","title":"Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stingy-teacher-sparse-logits-suffice-to-fail","title":"Stingy Teacher: Sparse Logits Suffice to Fail Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"to-smooth-or-not-to-smooth-on-compatibility","title":"To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-success-of-knowledge","title":"Understanding the Success of Knowledge Distillation -- A Data Augmentation Perspective","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wakening-past-concepts-without-past-data","title":"Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-to-whole-knowledge-distillation","title":"Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better","date":"2021-09-26","arxiv_id":"2109.12507","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-of-continual-learning-in","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","date":"2021-09-23","arxiv_id":"2109.11369","repositories_listed":0,"syntology":null},{"url":null,"slug":"k-aid-enhancing-pre-trained-language-models","title":"K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering","date":"2021-09-22","arxiv_id":"2109.10547","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-latency-incremental-text-to-speech","title":"Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network","date":"2021-09-22","arxiv_id":"2109.10724","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-niutrans-machine-translation-systems-for-1","title":"The NiuTrans Machine Translation Systems for WMT21","date":"2021-09-22","arxiv_id":"2109.10485","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-noisy-labels-for","title":"Knowledge Distillation with Noisy Labels for Natural Language Understanding","date":"2021-09-21","arxiv_id":"2109.10147","repositories_listed":0,"syntology":null},{"url":null,"slug":"rail-kd-random-intermediate-layer-mapping-for","title":"RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation","date":"2021-09-21","arxiv_id":"2109.10164","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-full-utilization-on-mask-task-for","title":"Towards Full Utilization on Mask Task for Distilling PLMs into NMT","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"label-assignment-distillation-for-object","title":"Label Assignment Distillation for Object Detection","date":"2021-09-16","arxiv_id":"2109.07843","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-perspective-on-progressive-gans","title":"New Perspective on Progressive GANs Distillation for One-class Novelty Detection","date":"2021-09-15","arxiv_id":"2109.07295","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignart-non-autoregressive-neural-machine","title":"AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate","date":"2021-09-14","arxiv_id":"2109.06481","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-accurate-simple-models-with-multihop","title":"Multihop: Leveraging Complex Models to Learn Accurate Simple Models","date":"2021-09-14","arxiv_id":"2109.06961","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-connection-between-knowledge","title":"A Note on Knowledge Distillation Loss Function for Object Classification","date":"2021-09-14","arxiv_id":"2109.06458","repositories_listed":0,"syntology":null},{"url":null,"slug":"secure-your-ride-real-time-matching-success","title":"Secure Your Ride: Real-time Matching Success Rate Prediction for Passenger-Driver Pairs","date":"2021-09-14","arxiv_id":"2109.07571","repositories_listed":0,"syntology":null},{"url":null,"slug":"kroneckerbert-learning-kronecker","title":"KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation","date":"2021-09-13","arxiv_id":"2109.06243","repositories_listed":0,"syntology":null},{"url":null,"slug":"unims-a-unified-framework-for-multimodal","title":"UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation","date":"2021-09-13","arxiv_id":"2109.05812","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-ensemble-model-based-reinforcement","title":"Federated Ensemble Model-based Reinforcement Learning in Edge Computing","date":"2021-09-12","arxiv_id":"2109.05549","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-efficiency-of-subclass-knowledge","title":"On the Efficiency of Subclass Knowledge Distillation in Classification Tasks","date":"2021-09-12","arxiv_id":"2109.05587","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-teach-with-student-feedback","title":"Learning to Teach with Student Feedback","date":"2021-09-10","arxiv_id":"2109.04641","repositories_listed":0,"syntology":null},{"url":"/paper/towards-developing-a-multilingual-and-code","slug":"towards-developing-a-multilingual-and-code","title":"Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation","date":"2021-09-10","arxiv_id":"2109.04653","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-learning-spatially-discriminative","title":"CAM-loss: Towards Learning Spatially Discriminative Feature Representations","date":"2021-09-03","arxiv_id":"2109.01359","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-transformer-for-scalable-inference-1","title":"Decoupled Transformer for Scalable Inference in Open-domain Question Answering","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-bert-for-image","title":"Knowledge Distillation with BERT for Image Tag-Based Privacy Prediction","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fedkd-communication-efficient-federated","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","date":"2021-08-30","arxiv_id":"2108.13323","repositories_listed":0,"syntology":null},{"url":null,"slug":"lipschitz-continuity-guided-knowledge","title":"Lipschitz Continuity Guided Knowledge Distillation","date":"2021-08-29","arxiv_id":"2108.12905","repositories_listed":0,"syntology":null},{"url":null,"slug":"coco-distillnet-a-cross-layer-correlation","title":"CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation","date":"2021-08-27","arxiv_id":"2108.12173","repositories_listed":0,"syntology":null},{"url":"/paper/sign-spatial-information-incorporated","slug":"sign-spatial-information-incorporated","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","date":"2021-08-27","arxiv_id":"2108.12517","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-training-of-lightweight-neural","title":"Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation","date":"2021-08-26","arxiv_id":"2108.11798","repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-a-bert-based-query-title-relevance","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","date":"2021-08-23","arxiv_id":"2108.10197","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalised-federated-learning-a","title":"Personalised Federated Learning: A Combinational Approach","date":"2021-08-22","arxiv_id":"2108.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-from-ensemble-of","title":"Boosting of Head Pose Estimation by Knowledge Distillation","date":"2021-08-20","arxiv_id":"2108.09183","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-learns-to-teach-knowledge-distillation","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"g-detkd-towards-general-distillation","title":"G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation","date":"2021-08-17","arxiv_id":"2108.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-continual-learning-for-visual-food","title":"Online Continual Learning For Visual Food Classification","date":"2021-08-15","arxiv_id":"2108.06781","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-matured-dumb-teacher-for-fine","title":"Learning from Matured Dumb Teacher for Fine Generalization","date":"2021-08-12","arxiv_id":"2108.05776","repositories_listed":0,"syntology":null},{"url":null,"slug":"preventing-catastrophic-forgetting-and","title":"Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data","date":"2021-08-11","arxiv_id":"2108.05698","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-intent-detection-via-multi-strategy","title":"Lifelong Intent Detection via Multi-Strategy Rebalancing","date":"2021-08-10","arxiv_id":"2108.04445","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-an-augmented-rgb-representation-with","title":"Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection","date":"2021-08-08","arxiv_id":"2108.03619","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-distillation-based-approach-for-the","title":"A distillation based approach for the diagnosis of diseases","date":"2021-08-07","arxiv_id":"2108.03470","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-attention-mechanism-and","title":"Spatio-Temporal Attention Mechanism and Knowledge Distillation for Lip Reading","date":"2021-08-07","arxiv_id":"2108.03543","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-transformer-for-scalable-inference","title":"Decoupled Transformer for Scalable Inference in Open-domain Question Answering","date":"2021-08-05","arxiv_id":"2108.02765","repositories_listed":0,"syntology":null},{"url":null,"slug":"ms-kd-multi-organ-segmentation-with-multiple","title":"MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets","date":"2021-08-05","arxiv_id":"2108.02559","repositories_listed":0,"syntology":null},{"url":null,"slug":"wechat-neural-machine-translation-systems-for-1","title":"WeChat Neural Machine Translation Systems for WMT21","date":"2021-08-05","arxiv_id":"2108.02401","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervising-learning-transfer-learning","title":"Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR","date":"2021-08-02","arxiv_id":"2108.00587","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-batch-negatives-for-knowledge-distillation","title":"In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense Retrieval","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-ceng-jian-zhi-shi-zheng-liu-de-shen","title":"基于层间知识蒸馏的神经机器翻译(Inter-layer Knowledge Distillation for Neural Machine Translation)","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"matching-distributions-between-model-and-data","title":"Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-strategy-knowledge-distillation-based","title":"Multi-Strategy Knowledge Distillation Based Teacher-Student Framework for Machine Reading Comprehension","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"naist-english-to-japanese-simultaneous","title":"NAIST English-to-Japanese Simultaneous Translation System for IWSLT 2021 Simultaneous Text-to-text Task","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-knowledge-distillation-for-translating","title":"On Knowledge Distillation for Translating Erroneous Speech Transcriptions","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pral-a-tailored-pre-training-model-for-task","title":"PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"samsung-r-d-institute-poland-submission-to","title":"Samsung R&D Institute Poland submission to WAT 2021 Indic Language Multilingual Task","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-usyd-jd-speech-translation-system-for-1","title":"The USYD-JD Speech Translation System for IWSLT2021","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"trigger-is-not-sufficient-exploiting-frame","title":"Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/pose-guided-feature-learning-with-knowledge","slug":"pose-guided-feature-learning-with-knowledge","title":"Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification","date":"2021-07-31","arxiv_id":"2108.00139","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-efficacy-of-small-self-supervised","title":"On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals","date":"2021-07-30","arxiv_id":"2107.14762","repositories_listed":0,"syntology":null},{"url":null,"slug":"quped-quantized-personalization-via","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","date":"2021-07-29","arxiv_id":"2107.13892","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-perturbed-length-aware-positional","title":"Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation","date":"2021-07-29","arxiv_id":"2107.13689","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-defense-of-the-learning-without-forgetting","title":"In Defense of the Learning Without Forgetting for Task Incremental Learning","date":"2021-07-26","arxiv_id":"2107.12304","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-is-text-no-matter-what-unifying-text","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","date":"2021-07-26","arxiv_id":"2107.12087","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-usyd-jd-speech-translation-system-for","title":"The USYD-JD Speech Translation System for IWSLT 2021","date":"2021-07-24","arxiv_id":"2107.11572","repositories_listed":0,"syntology":null},{"url":null,"slug":"follow-your-path-a-progressive-method-for","title":"Follow Your Path: a Progressive Method for Knowledge Distillation","date":"2021-07-20","arxiv_id":"2107.09305","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-ulmfit-and-self-distillation-with","title":"Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System","date":"2021-07-20","arxiv_id":"2107.09625","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-similarity-distillation-for-semantic","title":"Double Similarity Distillation for Semantic Image Segmentation","date":"2021-07-19","arxiv_id":"2107.08591","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-action-recognition-on-heterogeneous","title":"Federated Action Recognition on Heterogeneous Embedded Devices","date":"2021-07-18","arxiv_id":"2107.12147","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-adaptive-knowledge-distillation-for","title":"Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search","date":"2021-07-15","arxiv_id":"2107.07173","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-translation-by-understanding","title":"Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task","date":"2021-07-12","arxiv_id":"2107.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-of-team-graphmiracles-in-the","title":"Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021","date":"2021-07-12","arxiv_id":"2107.05476","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrast-r-cnn-for-continual-learning-in","title":"Contrast R-CNN for Continual Learning in Object Detection","date":"2021-07-11","arxiv_id":"2108.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-twin-generative-adversarial-networks","title":"Lifelong Twin Generative Adversarial Networks","date":"2021-07-09","arxiv_id":"2107.04708","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-visual-category-discovery-with-dual","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","date":"2021-07-07","arxiv_id":"2107.03358","repositories_listed":0,"syntology":null},{"url":null,"slug":"weclick-weakly-supervised-video-semantic","title":"WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations","date":"2021-07-07","arxiv_id":"2107.03088","repositories_listed":0,"syntology":null}],"record_sha256":"82a76a78abdccf3d43b20fc8cbbc8f3335bb7e519faed24dad488756516925bc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}