{"total":187,"rows":[{"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":"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":"2204.06986","title":"Cross-Image Relational Knowledge Distillation for Semantic Segmentation","created":"2022-04-14","cited_by_count":118,"area":"distill"},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112,"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":"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":"2107.01378","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","created":"2021-07-03","cited_by_count":60,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2109.12484","title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","created":"2021-09-26","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":"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":"2210.03664","title":"Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification","created":"2022-10-07","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":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37,"area":"distill"},{"id":"2207.11518","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","created":"2022-07-23","cited_by_count":36,"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":"2312.13789","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","created":"2023-12-21","cited_by_count":33,"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":"2208.05768","title":"MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition","created":"2022-08-11","cited_by_count":30,"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":"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":"2108.05507","title":"Distilling Holistic Knowledge with Graph Neural Networks","created":"2021-08-12","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":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"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":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2210.17332","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","created":"2022-10-28","cited_by_count":23,"area":"distill"},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"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":"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":"2206.02325","title":"Evaluation-oriented Knowledge Distillation for Deep Face Recognition","created":"2022-06-06","cited_by_count":19,"area":"distill"},{"id":"2308.09922","title":"MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition","created":"2023-08-19","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":"2106.13266","title":"DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval","created":"2021-06-24","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":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16,"area":"distill"},{"id":"2107.00181","title":"Revisiting Knowledge Distillation: An Inheritance and Exploration Framework","created":"2021-07-01","cited_by_count":15,"area":"distill"},{"id":"2402.17110","title":"Sinkhorn Distance Minimization for Knowledge Distillation","created":"2024-02-27","cited_by_count":15,"area":"distill"},{"id":"2208.14143","title":"FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation","created":"2022-08-30","cited_by_count":14,"area":"distill"},{"id":"2104.15082","title":"Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation","created":"2021-04-30","cited_by_count":13,"area":"distill"},{"id":"2109.03075","title":"Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution","created":"2021-09-07","cited_by_count":13,"area":"distill"},{"id":"2203.11490","title":"SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images","created":"2022-03-22","cited_by_count":12,"area":"distill"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"id":"2207.05345","title":"HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors","created":"2022-07-12","cited_by_count":12,"area":"distill"},{"id":"2203.13452","title":"PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models","created":"2022-03-25","cited_by_count":11,"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":"2309.13220","title":"Poster: Self-Supervised Quantization-Aware Knowledge Distillation","created":"2023-09-22","cited_by_count":11,"area":"distill"},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","cited_by_count":11,"area":"distill"},{"id":"2503.18244","title":"CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation","created":"2025-03-23","cited_by_count":11,"area":"distill"},{"id":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","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":"2111.11747","title":"Semi-Online Knowledge Distillation","created":"2021-11-23","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":"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":"2407.01332","title":"AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition","created":"2024-07-01","cited_by_count":8,"area":"distill"},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2212.08974","title":"3D Point Cloud Pre-training with Knowledge Distillation from 2D Images","created":"2022-12-17","cited_by_count":7,"area":"distill"},{"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":"2404.14109","title":"CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective","created":"2024-04-22","cited_by_count":7,"area":"distill"},{"id":"2411.01547","title":"Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment","created":"2024-11-03","cited_by_count":7,"area":"distill"},{"id":"2110.15946","title":"Estimating and Maximizing Mutual Information for Knowledge Distillation","created":"2021-10-29","cited_by_count":6,"area":"distill"},{"id":"2204.08922","title":"Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring","created":"2022-04-01","cited_by_count":6,"area":"distill"},{"id":"2302.14643","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","created":"2023-02-27","cited_by_count":6,"area":"distill"},{"id":"2303.09230","title":"Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval","created":"2023-03-16","cited_by_count":6,"area":"distill"},{"id":"2308.16561","title":"MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis","created":"2023-08-31","cited_by_count":6,"area":"distill"},{"id":"2502.20760","title":"VRM: Knowledge Distillation via Virtual Relation Matching","created":"2025-02-28","cited_by_count":6,"area":"distill"},{"id":"2503.08038","title":"Generalized Kullback-Leibler Divergence Loss","created":"2025-03-11","cited_by_count":6,"area":"distill"},{"id":"2108.12173","title":"CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation","created":"2021-08-27","cited_by_count":5,"area":"distill"},{"id":"2202.12488","title":"Learn From the Past: Experience Ensemble Knowledge Distillation","created":"2022-02-25","cited_by_count":5,"area":"distill"},{"id":"2211.03946","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","created":"2022-11-08","cited_by_count":5,"area":"distill"},{"id":"2212.05422","title":"Teaching What You Should Teach: A Data-Based Distillation Method","created":"2022-12-11","cited_by_count":5,"area":"distill"},{"id":"2301.05849","title":"Knowledge Distillation in Federated Edge Learning: A Survey","created":"2023-01-14","cited_by_count":5,"area":"distill"},{"id":"2306.17424","title":"Audio Embeddings as Teachers for Music Classification","created":"2023-06-30","cited_by_count":5,"area":"distill"},{"id":"2311.14307","title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","created":"2023-11-24","cited_by_count":5,"area":"distill"},{"id":"2405.18524","title":"Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures","created":"2024-05-28","cited_by_count":5,"area":"distill"},{"id":"2409.13939","title":"Simple Unsupervised Knowledge Distillation With Space Similarity","created":"2024-09-20","cited_by_count":5,"area":"distill"},{"id":"2412.16493","title":"Cross-View Consistency Regularisation for Knowledge Distillation","created":"2024-12-21","cited_by_count":5,"area":"distill"},{"id":"2501.08885","title":"Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation","created":"2025-01-15","cited_by_count":5,"area":"distill"},{"id":"2107.03088","title":"WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations","created":"2021-07-07","cited_by_count":4,"area":"distill"},{"id":"2109.05587","title":"On the Efficiency of Subclass Knowledge Distillation in Classification Tasks","created":"2021-09-12","cited_by_count":4,"area":"distill"},{"id":"2207.01900","title":"ACT-Net: Asymmetric Co-Teacher Network for Semi-supervised Memory-efficient Medical Image Segmentation","created":"2022-07-05","cited_by_count":4,"area":"distill"},{"id":"2311.02253","title":"Comparative Knowledge Distillation","created":"2023-11-03","cited_by_count":4,"area":"distill"},{"id":"2405.13078","title":"Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch","created":"2024-05-21","cited_by_count":4,"area":"distill"}],"next_cursor":"100"}