{"total":516,"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":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288,"area":"distill"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208,"area":"distill"},{"id":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2111.11837","title":"Focal and Global Knowledge Distillation for Detectors","created":"2021-11-23","cited_by_count":142,"area":"distill"},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"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":"2206.02099","title":"Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation","created":"2022-06-05","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":"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":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108,"area":null},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"area":"distill"},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2104.00232","title":"Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition","created":"2021-04-01","cited_by_count":89,"area":null},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80,"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":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2205.10793","title":"Knowledge Distillation via the Target-aware Transformer","created":"2022-05-22","cited_by_count":70,"area":"distill"},{"id":"2203.17261","title":"R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis","created":"2022-03-31","cited_by_count":69,"area":null},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62,"area":null},{"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":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58,"area":null},{"id":"2103.12462","title":"Lifelong Person Re-Identification via Adaptive Knowledge Accumulation","created":"2021-03-23","cited_by_count":57,"area":null},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2203.14956","title":"LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"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":"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":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40,"area":null},{"id":"2205.05675","title":"NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results","created":"2022-05-11","cited_by_count":40,"area":null},{"id":"2304.08028","title":"MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning","created":"2023-04-17","cited_by_count":40,"area":null},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2203.06321","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","created":"2022-03-12","cited_by_count":39,"area":"distill"},{"id":"2208.11148","title":"Multi-domain Learning for Updating Face Anti-spoofing Models","created":"2022-08-23","cited_by_count":39,"area":null},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39,"area":null},{"id":"2101.08467","title":"CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification","created":"2021-01-21","cited_by_count":38,"area":null},{"id":"2111.04964","title":"On Representation Knowledge Distillation for Graph Neural Networks","created":"2021-11-09","cited_by_count":38,"area":"distill"},{"id":"2208.12448","title":"CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation","created":"2022-08-26","cited_by_count":38,"area":null},{"id":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37,"area":"distill"},{"id":"2212.13979","title":"TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning","created":"2022-12-28","cited_by_count":37,"area":null},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","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":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33,"area":null},{"id":"2104.10602","title":"Visualizing Adapted Knowledge in Domain Transfer","created":"2021-04-20","cited_by_count":32,"area":null},{"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":"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":"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":"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":"2103.14431","title":"Multimodal Knowledge Expansion","created":"2021-03-26","cited_by_count":26,"area":"distill"},{"id":"2108.05507","title":"Distilling Holistic Knowledge with Graph Neural Networks","created":"2021-08-12","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":"2112.01849","title":"Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition","created":"2021-10-08","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":"2106.08700","title":"Topology Distillation for Recommender System","created":"2021-06-16","cited_by_count":24,"area":"distill"},{"id":"2109.00946","title":"Adversarial Robustness for Unsupervised Domain Adaptation","created":"2021-09-02","cited_by_count":24,"area":null},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","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":"2404.04936","title":"Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models","created":"2024-04-07","cited_by_count":24,"area":null},{"id":"2204.11830","title":"Proto2Proto: Can you recognize the car, the way I do?","created":"2022-04-25","cited_by_count":23,"area":null},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2308.06217","title":"Continual Face Forgery Detection via Historical Distribution Preserving","created":"2023-08-11","cited_by_count":23,"area":null},{"id":"2104.09866","title":"Distill on the Go: Online knowledge distillation in self-supervised learning","created":"2021-04-20","cited_by_count":22,"area":"distill"},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"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":"2304.01279","title":"Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation","created":"2023-04-03","cited_by_count":22,"area":"moe"},{"id":"2504.09228","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","created":"2025-04-12","cited_by_count":22,"area":null},{"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":"2304.14122","title":"Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification","created":"2023-04-27","cited_by_count":21,"area":null},{"id":"2207.05306","title":"Contrastive Deep Supervision","created":"2022-07-12","cited_by_count":20,"area":null},{"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":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2108.12905","title":"Lipschitz Continuity Guided Knowledge Distillation","created":"2021-08-29","cited_by_count":19,"area":"distill"},{"id":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"}],"next_cursor":"100"}