{"list":"other","total":108,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"1806.01246","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","created":"2018-06-04","cited_by_count":498},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1910.07738","title":"A Survey of Deep Learning Techniques for Autonomous Driving","created":"2019-10-17","cited_by_count":403},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"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":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"1811.10959","title":"Dataset Distillation","created":"2018-11-27","cited_by_count":230},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"1905.12173","title":"On the Inductive Bias of Neural Tangent Kernels","created":"2019-05-29","cited_by_count":177},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"1512.08571","title":"Structured Pruning of Deep Convolutional Neural Networks","created":"2015-12-29","cited_by_count":149},{"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":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"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":"1801.05852","title":"Network Representation Learning: A Survey","created":"2017-12-04","cited_by_count":101},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100},{"id":"1512.00809","title":"Optimal whitening and decorrelation","created":"2015-12-02","cited_by_count":97},{"id":"2006.08572","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","created":"2020-06-15","cited_by_count":91},{"id":"1802.04889","title":"Understanding Membership Inferences on Well-Generalized Learning Models","created":"2018-02-13","cited_by_count":90},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"1912.00195","title":"SGAS: Sequential Greedy Architecture Search","created":"2019-11-30","cited_by_count":69},{"id":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","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":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62},{"id":"2206.13697","title":"Graph Condensation via Receptive Field Distribution Matching","created":"2022-06-28","cited_by_count":60},{"id":"1605.04988","title":"Going Deeper into Action Recognition: A Survey","created":"2016-05-16","cited_by_count":55},{"id":"2008.04489","title":"Federated Learning via Synthetic Data","created":"2020-08-11","cited_by_count":54},{"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":"1901.09290","title":"PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration","created":"2019-01-26","cited_by_count":41},{"id":"2208.00311","title":"Delving into Effective Gradient Matching for Dataset Condensation","created":"2022-07-30","cited_by_count":40},{"id":"2103.15851","title":"Distilled Replay: Overcoming Forgetting through Synthetic Samples","created":"2021-03-29","cited_by_count":36},{"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":"1706.06197","title":"meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting","created":"2017-06-19","cited_by_count":34},{"id":"2208.10494","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","created":"2022-08-21","cited_by_count":34},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","cited_by_count":31},{"id":"2206.11849","title":"Sample Condensation in Online Continual Learning","created":"2022-06-23","cited_by_count":31},{"id":"2209.14851","title":"Meta Knowledge Condensation for Federated Learning","created":"2022-09-29","cited_by_count":26},{"id":"2104.08448","title":"Data Distillation for Text Classification","created":"2021-04-17","cited_by_count":25},{"id":"2209.14603","title":"Dataset Distillation for Medical Dataset Sharing","created":"2022-09-29","cited_by_count":25},{"id":"1807.00301","title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","created":"2018-07-01","cited_by_count":24},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23},{"id":"2209.14987","title":"No Free Lunch in \"Privacy for Free: How does Dataset Condensation Help Privacy\"","created":"2022-09-29","cited_by_count":23},{"id":"2211.10878","title":"DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics","created":"2022-11-20","cited_by_count":22}],"next_cursor":"100"}