{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"1708.02709","title":"Recent Trends in Deep Learning Based Natural Language Processing","created":"2017-08-09","cited_by_count":263},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2003.04919","title":"Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems","created":"2020-03-10","cited_by_count":164},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"1910.02551","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","created":"2019-10-06","cited_by_count":107},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100},{"id":"2006.08572","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","created":"2020-06-15","cited_by_count":91},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"2102.01998","title":"Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond","created":"2021-02-03","cited_by_count":76},{"id":"2207.09653","title":"FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning","created":"2022-07-20","cited_by_count":66},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51},{"id":"2208.11311","title":"Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments","created":"2022-08-24","cited_by_count":49},{"id":"1902.08691","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","created":"2019-02-22","cited_by_count":48},{"id":"2208.00311","title":"Delving into Effective Gradient Matching for Dataset Condensation","created":"2022-07-30","cited_by_count":40},{"id":"2209.07507","title":"Bidirectional Learning for Offline Infinite-width Model-based Optimization","created":"2022-09-15","cited_by_count":35},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","cited_by_count":35},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34},{"id":"2206.11849","title":"Sample Condensation in Online Continual Learning","created":"2022-06-23","cited_by_count":31},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30},{"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":"2209.14603","title":"Dataset Distillation for Medical Dataset Sharing","created":"2022-09-29","cited_by_count":25},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21},{"id":"2102.09890","title":"Condensed Composite Memory Continual Learning","created":"2021-02-19","cited_by_count":20},{"id":"2301.02931","title":"Bidirectional Learning for Offline Model-based Biological Sequence Design","created":"2023-01-07","cited_by_count":20},{"id":"2304.01534","title":"FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems","created":"2023-04-04","cited_by_count":14},{"id":"2206.03009","title":"Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images","created":"2022-06-07","cited_by_count":13},{"id":"2211.10752","title":"Towards Robust Dataset Learning","created":"2022-11-19","cited_by_count":9},{"id":"2206.03012","title":"TriBYOL: Triplet BYOL for Self-Supervised Representation Learning","created":"2022-06-07","cited_by_count":8},{"id":"2212.09276","title":"COVID-19 Detection Based on Self-Supervised Transfer Learning Using Chest X-Ray Images","created":"2022-12-19","cited_by_count":7},{"id":"2112.13443","title":"Sinogram upsampling using Primal-Dual UNet for undersampled CT and radial MRI reconstruction","created":"2021-12-26","cited_by_count":6},{"id":"1909.08069","title":"Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities","created":"2019-09-02","cited_by_count":1}],"next_cursor":null}