{"total":391,"rows":[{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288,"area":"distill"},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208,"area":"distill"},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"area":"distill"},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134,"area":"distill"},{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119,"area":"distill"},{"id":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114,"area":"distill"},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112,"area":"distill"},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107,"area":"distill"},{"id":"2107.03358","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","created":"2021-07-07","cited_by_count":104,"area":"distill"},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"area":"distill"},{"id":"2102.02973","title":"Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching","created":"2021-02-05","cited_by_count":79,"area":"distill"},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78,"area":"distill"},{"id":"2205.10793","title":"Knowledge Distillation via the Target-aware Transformer","created":"2022-05-22","cited_by_count":70,"area":"distill"},{"id":"2303.13005","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","created":"2023-03-23","cited_by_count":69,"area":"distill"},{"id":"2211.09386","title":"BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection","created":"2022-11-17","cited_by_count":66,"area":"distill"},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61,"area":"distill"},{"id":"2304.12777","title":"Class Attention Transfer Based Knowledge Distillation","created":"2023-04-25","cited_by_count":61,"area":"distill"},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60,"area":"distill"},{"id":"2106.04411","title":"Fair Feature Distillation for Visual Recognition","created":"2021-05-27","cited_by_count":59,"area":"distill"},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50,"area":"distill"},{"id":"2112.03553","title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","created":"2021-12-07","cited_by_count":48,"area":"distill"},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2103.08273","title":"Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation","created":"2021-03-15","cited_by_count":46,"area":"distill"},{"id":"2105.07519","title":"Graph-Free Knowledge Distillation for Graph Neural Networks","created":"2021-05-16","cited_by_count":46,"area":"distill"},{"id":"2209.03917","title":"Exploring Target Representations for Masked Autoencoders","created":"2022-09-08","cited_by_count":46,"area":"distill"},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44,"area":"distill"},{"id":"2107.13715","title":"Hierarchical Self-supervised Augmented Knowledge Distillation","created":"2021-07-29","cited_by_count":44,"area":"distill"},{"id":"2202.03680","title":"Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation","created":"2022-02-08","cited_by_count":44,"area":"distill"},{"id":"2206.06487","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","created":"2022-06-13","cited_by_count":44,"area":"distill"},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"area":"distill"},{"id":"2108.09987","title":"Efficient Medical Image Segmentation Based on Knowledge Distillation","created":"2021-08-23","cited_by_count":43,"area":"distill"},{"id":"2103.16367","title":"Complementary Relation Contrastive Distillation","created":"2021-03-29","cited_by_count":42,"area":"distill"},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41,"area":"distill"},{"id":"2207.02039","title":"PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient","created":"2022-07-05","cited_by_count":41,"area":"distill"},{"id":"2207.05273","title":"Cross-Architecture Knowledge Distillation","created":"2022-07-12","cited_by_count":41,"area":"distill"},{"id":"2201.00007","title":"Confidence-Aware Multi-Teacher Knowledge Distillation","created":"2021-12-30","cited_by_count":39,"area":"distill"},{"id":"2203.06321","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","created":"2022-03-12","cited_by_count":39,"area":"distill"},{"id":"2111.04964","title":"On Representation Knowledge Distillation for Graph Neural Networks","created":"2021-11-09","cited_by_count":38,"area":"distill"},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37,"area":"distill"},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36,"area":"distill"},{"id":"2209.02432","title":"ViTKD: Practical Guidelines for ViT feature knowledge distillation","created":"2022-09-06","cited_by_count":34,"area":"distill"},{"id":"2205.11098","title":"PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection","created":"2022-05-23","cited_by_count":33,"area":"distill"},{"id":"2108.03619","title":"Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection","created":"2021-08-08","cited_by_count":32,"area":"distill"},{"id":"2110.15094","title":"Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data","created":"2021-10-27","cited_by_count":32,"area":"distill"},{"id":"2211.17068","title":"Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces","created":"2022-11-30","cited_by_count":32,"area":"distill"},{"id":"2404.16456","title":"Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","created":"2024-04-25","cited_by_count":32,"area":"distill"},{"id":"2209.10359","title":"Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation","created":"2022-09-21","cited_by_count":31,"area":"distill"},{"id":"2303.11098","title":"Understanding the Role of the Projector in Knowledge Distillation","created":"2023-03-20","cited_by_count":31,"area":"distill"},{"id":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"area":"distill"},{"id":"2203.16172","title":"Self-Distillation from the Last Mini-Batch for Consistency Regularization","created":"2022-03-30","cited_by_count":29,"area":"distill"},{"id":"2209.04996","title":"Switchable Online Knowledge Distillation","created":"2022-09-12","cited_by_count":29,"area":"distill"},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2108.07482","title":"G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation","created":"2021-08-17","cited_by_count":28,"area":"distill"},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2210.15274","title":"Improved Feature Distillation via Projector Ensemble","created":"2022-10-27","cited_by_count":27,"area":"distill"},{"id":"2408.05088","title":"UNIC: Universal Classification Models via Multi-teacher Distillation","created":"2024-08-09","cited_by_count":27,"area":"distill"},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27,"area":"distill"},{"id":"2108.05507","title":"Distilling Holistic Knowledge with Graph Neural Networks","created":"2021-08-12","cited_by_count":26,"area":"distill"},{"id":"2207.05500","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","created":"2022-07-12","cited_by_count":26,"area":"distill"},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25,"area":"distill"},{"id":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2105.11683","title":"Towards Compact Single Image Super-Resolution via Contrastive Self-distillation","created":"2021-05-25","cited_by_count":24,"area":"distill"},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24,"area":"distill"},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2403.05894","title":"Frequency Attention for Knowledge Distillation","created":"2024-03-09","cited_by_count":24,"area":"distill"},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2307.09158","title":"Class-relation Knowledge Distillation for Novel Class Discovery","created":"2023-07-18","cited_by_count":23,"area":"distill"},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22,"area":"distill"},{"id":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22,"area":"distill"},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"area":"distill"},{"id":"2201.05131","title":"SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation","created":"2022-01-13","cited_by_count":21,"area":"distill"},{"id":"2203.05180","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","created":"2022-03-10","cited_by_count":21,"area":"distill"},{"id":"2304.11832","title":"Function-Consistent Feature Distillation","created":"2023-04-24","cited_by_count":21,"area":"distill"},{"id":"2202.07940","title":"Meta Knowledge Distillation","created":"2022-02-16","cited_by_count":20,"area":"distill"},{"id":"2207.05409","title":"Knowledge Condensation Distillation","created":"2022-07-12","cited_by_count":20,"area":"distill"},{"id":"2304.06461","title":"Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning","created":"2023-04-13","cited_by_count":20,"area":"distill"},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20,"area":"distill"},{"id":"2108.12905","title":"Lipschitz Continuity Guided Knowledge Distillation","created":"2021-08-29","cited_by_count":19,"area":"distill"},{"id":"2109.10164","title":"RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation","created":"2021-09-21","cited_by_count":19,"area":"distill"},{"id":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19,"area":"distill"},{"id":"2207.10425","title":"KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo","created":"2022-07-21","cited_by_count":18,"area":"distill"},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2305.17007","title":"Improving Knowledge Distillation via Regularizing Feature Norm and Direction","created":"2023-05-26","cited_by_count":18,"area":"distill"},{"id":"2307.08500","title":"Cumulative Spatial Knowledge Distillation for Vision Transformers","created":"2023-07-17","cited_by_count":18,"area":"distill"},{"id":"2309.02870","title":"Rethinking Momentum Knowledge Distillation in Online Continual Learning","created":"2023-09-06","cited_by_count":18,"area":"distill"},{"id":"2211.09768","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","created":"2022-11-17","cited_by_count":17,"area":"distill"},{"id":"2401.11824","title":"Rethinking Centered Kernel Alignment in Knowledge Distillation","created":"2024-01-22","cited_by_count":17,"area":"distill"},{"id":"2104.13298","title":"Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification","created":"2021-04-27","cited_by_count":16,"area":"distill"},{"id":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16,"area":"distill"},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2303.07815","title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","created":"2023-03-14","cited_by_count":16,"area":"distill"},{"id":"2306.06634","title":"Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning","created":"2023-06-11","cited_by_count":16,"area":"distill"}],"next_cursor":"100"}