{"total":288,"rows":[{"id":"2201.10703","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","created":"2022-01-26","cited_by_count":421,"area":"distill"},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"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":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"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":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"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":"2204.02136","title":"Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation","created":"2022-04-05","cited_by_count":72,"area":null},{"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":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68,"area":null},{"id":"2304.12777","title":"Class Attention Transfer Based Knowledge Distillation","created":"2023-04-25","cited_by_count":61,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53,"area":"diffusion"},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"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":"2207.05273","title":"Cross-Architecture Knowledge Distillation","created":"2022-07-12","cited_by_count":41,"area":"distill"},{"id":"2310.08255","title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","created":"2023-10-12","cited_by_count":41,"area":"mllm"},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37,"area":"distill"},{"id":"2211.10156","title":"DETRDistill: A Universal Knowledge Distillation Framework for DETR-families","created":"2022-11-17","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":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33,"area":"mllm"},{"id":"2209.04996","title":"Switchable Online Knowledge Distillation","created":"2022-09-12","cited_by_count":29,"area":"distill"},{"id":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28,"area":"alignment"},{"id":"2210.15274","title":"Improved Feature Distillation via Projector Ensemble","created":"2022-10-27","cited_by_count":27,"area":"distill"},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2306.15925","title":"Subclass-balancing Contrastive Learning for Long-tailed Recognition","created":"2023-06-28","cited_by_count":26,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","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":"2207.10024","title":"Difficulty-Aware Simulator for Open Set Recognition","created":"2022-07-20","cited_by_count":24,"area":null},{"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":"2206.14971","title":"Boosting 3D Object Detection by Simulating Multimodality on Point Clouds","created":"2022-06-30","cited_by_count":22,"area":null},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21,"area":null},{"id":"2304.11832","title":"Function-Consistent Feature Distillation","created":"2023-04-24","cited_by_count":21,"area":"distill"},{"id":"2305.12954","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","created":"2023-05-22","cited_by_count":21,"area":"diffusion"},{"id":"2207.05409","title":"Knowledge Condensation Distillation","created":"2022-07-12","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":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"},{"id":"2302.14771","title":"Generic-to-Specific Distillation of Masked Autoencoders","created":"2023-02-28","cited_by_count":19,"area":null},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19,"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":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17,"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":"2308.15122","title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","created":"2023-08-29","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":"2404.09571","title":"MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution","created":"2024-04-15","cited_by_count":17,"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":"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":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2212.14284","title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","created":"2022-12-29","cited_by_count":15,"area":null},{"id":"2404.08564","title":"Federated Distillation: A Survey","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2210.06771","title":"Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13,"area":"distill"},{"id":"2407.18041","title":"How to Train the Teacher Model for Effective Knowledge Distillation","created":"2024-07-25","cited_by_count":13,"area":"distill"},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12,"area":null},{"id":"2308.00520","title":"NormKD: Normalized Logits for Knowledge Distillation","created":"2023-08-01","cited_by_count":12,"area":"distill"},{"id":"2308.06453","title":"Multi-Label Knowledge Distillation","created":"2023-08-12","cited_by_count":12,"area":"distill"},{"id":"2305.10893","title":"Student-friendly Knowledge Distillation","created":"2023-05-18","cited_by_count":11,"area":"distill"},{"id":"2305.15781","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","created":"2023-05-25","cited_by_count":11,"area":"distill"},{"id":"2306.14818","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","created":"2023-06-26","cited_by_count":11,"area":"distill"},{"id":"2312.16279","title":"Cloud-Device Collaborative Learning for Multimodal Large Language Models","created":"2023-12-26","cited_by_count":11,"area":"lr"},{"id":"2402.17316","title":"Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","cited_by_count":11,"area":"distill"},{"id":"2602.17951","title":"ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models","created":"2026-02-20","cited_by_count":11,"area":"vla"},{"id":"2306.15110","title":"Deep Transfer Learning for Intelligent Vehicle Perception: a Survey","created":"2023-06-26","cited_by_count":10,"area":null},{"id":"2309.16460","title":"Diverse Target and Contribution Scheduling for Domain Generalization","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2403.01238","title":"On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving","created":"2024-03-02","cited_by_count":10,"area":"driving"},{"id":"2408.15641","title":"MMDRFuse: Distilled Mini-Model with Dynamic Refresh for Multi-Modality Image Fusion","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2506.15681","title":"GenRecal: Generation after Recalibration from Large to Small Vision-Language Models","created":"2025-06-18","cited_by_count":10,"area":"mllm"},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9,"area":"distill"},{"id":"2308.14852","title":"SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data","created":"2023-08-28","cited_by_count":9,"area":"distill"},{"id":"2309.08144","title":"Two-Step Knowledge Distillation for Tiny Speech Enhancement","created":"2023-09-15","cited_by_count":9,"area":"distill"},{"id":"2406.10861","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","created":"2024-06-16","cited_by_count":9,"area":"distill"},{"id":"2408.07703","title":"Knowledge Distillation with Refined Logits","created":"2024-08-14","cited_by_count":9,"area":"distill"},{"id":"2506.17290","title":"SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation","created":"2025-06-16","cited_by_count":9,"area":"distill"},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8,"area":"distill"},{"id":"2307.11469","title":"Distribution Shift Matters for Knowledge Distillation with Webly Collected Images","created":"2023-07-21","cited_by_count":8,"area":"distill"},{"id":"2311.13621","title":"EA-KD: Entropy-based Adaptive Knowledge Distillation","created":"2023-11-22","cited_by_count":8,"area":"distill"},{"id":"2401.06826","title":"Direct Distillation between Different Domains","created":"2024-01-12","cited_by_count":8,"area":"distill"},{"id":"2403.08215","title":"LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving","created":"2024-03-13","cited_by_count":8,"area":"distill"},{"id":"2409.12111","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","created":"2024-09-18","cited_by_count":8,"area":"distill"},{"id":"2204.05547","title":"DistPro: Searching A Fast Knowledge Distillation Process via Meta Optimization","created":"2022-04-12","cited_by_count":7,"area":"distill"},{"id":"2301.01615","title":"StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2305.05233","title":"DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing","created":"2023-05-09","cited_by_count":7,"area":"distill"},{"id":"2308.07575","title":"Story Visualization by Online Text Augmentation with Context Memory","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2401.00523","title":"Compressing Deep Image Super-resolution Models","created":"2023-12-31","cited_by_count":7,"area":"distill"},{"id":"2404.14109","title":"CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective","created":"2024-04-22","cited_by_count":7,"area":"distill"}],"next_cursor":"100"}