{"list":"other","total":154,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2202.00273","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","created":"2022-02-01","cited_by_count":492},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2007.08745","title":"Backdoor Learning: A Survey","created":"2020-07-17","cited_by_count":426},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2302.03660","title":"Flow Matching on General Geometries","created":"2023-02-07","cited_by_count":265},{"id":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207},{"id":"1806.05500","title":"Statistical Aspects of Wasserstein Distances","created":"2018-06-14","cited_by_count":203},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109},{"id":"2112.12371","title":"DENSE: Data-Free One-Shot Federated Learning","created":"2021-12-23","cited_by_count":100},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2107.03055","title":"Blind Image Super-Resolution: A Survey and Beyond","created":"2021-07-07","cited_by_count":93},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"2407.15138","title":"D$^4$M: Dataset Distillation via Disentangled Diffusion Model","created":"2024-07-21","cited_by_count":77},{"id":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67},{"id":"2207.09653","title":"FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning","created":"2022-07-20","cited_by_count":66},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50},{"id":"2208.11311","title":"Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments","created":"2022-08-24","cited_by_count":49},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2303.04707","title":"DiM: Distilling Dataset into Generative Model","created":"2023-03-08","cited_by_count":46},{"id":"2311.01570","title":"Sequential Subset Matching for Dataset Distillation","created":"2023-11-02","cited_by_count":40},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2404.18962","title":"An Aggregation-Free Federated Learning for Tackling Data Heterogeneity","created":"2024-04-29","cited_by_count":33},{"id":"2409.17612","title":"Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment","created":"2024-09-26","cited_by_count":33},{"id":"2305.01975","title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","created":"2023-05-03","cited_by_count":32},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","cited_by_count":31},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31},{"id":"2404.00563","title":"Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation","created":"2024-03-31","cited_by_count":31},{"id":"2406.10485","title":"A Label is Worth a Thousand Images in Dataset Distillation","created":"2024-06-15","cited_by_count":31},{"id":"2311.08819","title":"Frequency Domain-based Dataset Distillation","created":"2023-11-15","cited_by_count":28},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27},{"id":"2209.14851","title":"Meta Knowledge Condensation for Federated Learning","created":"2022-09-29","cited_by_count":26},{"id":"2407.14245","title":"Dataset Distillation by Automatic Training Trajectories","created":"2024-07-19","cited_by_count":26},{"id":"2403.03881","title":"Unlocking Dataset Distillation with Diffusion Models","created":"2024-03-06","cited_by_count":23},{"id":"2211.10878","title":"DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics","created":"2022-11-20","cited_by_count":22},{"id":"2406.18561","title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","created":"2024-05-28","cited_by_count":22},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21},{"id":"2312.00362","title":"Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement","created":"2023-12-01","cited_by_count":21},{"id":"2312.16627","title":"MIM4DD: Mutual Information Maximization for Dataset Distillation","created":"2023-12-27","cited_by_count":21},{"id":"2405.11525","title":"Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors","created":"2024-05-19","cited_by_count":21},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2411.19946","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","created":"2024-11-29","cited_by_count":20},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19},{"id":"2410.15919","title":"Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?","created":"2024-10-21","cited_by_count":19},{"id":"2401.15863","title":"Importance-Aware Adaptive Dataset Distillation","created":"2024-01-29","cited_by_count":18},{"id":"2404.17732","title":"Generative Dataset Distillation: Balancing Global Structure and Local Details","created":"2024-04-26","cited_by_count":18},{"id":"2410.17193","title":"Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios","created":"2024-10-22","cited_by_count":18},{"id":"2403.10045","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","created":"2024-03-15","cited_by_count":17},{"id":"2406.03793","title":"Low-Rank Similarity Mining for Multimodal Dataset Distillation","created":"2024-06-06","cited_by_count":17},{"id":"2312.01537","title":"Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents","created":"2023-12-03","cited_by_count":16},{"id":"2309.07698","title":"Dataset Condensation via Generative Model","created":"2023-09-14","cited_by_count":15},{"id":"2406.01063","title":"DANCE: Dual-View Distribution Alignment for Dataset Condensation","created":"2024-06-03","cited_by_count":15},{"id":"2307.09165","title":"Towards Trustworthy Dataset Distillation","created":"2023-07-18","cited_by_count":14},{"id":"2404.07976","title":"Self-supervised Dataset Distillation: A Good Compression Is All You Need","created":"2024-04-11","cited_by_count":14},{"id":"2408.12483","title":"Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation","created":"2024-08-22","cited_by_count":14},{"id":"2408.16236","title":"Neural Spectral Decomposition for Dataset Distillation","created":"2024-08-29","cited_by_count":14},{"id":"2501.07575","title":"Dataset Distillation via Committee Voting","created":"2025-01-13","cited_by_count":14},{"id":"2406.04284","title":"What is Dataset Distillation Learning?","created":"2024-06-06","cited_by_count":13},{"id":"2408.06927","title":"Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator","created":"2024-08-13","cited_by_count":13}],"next_cursor":"100"}