{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","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":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"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":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1812.06162","title":"An Empirical Model of Large-Batch Training","created":"2018-12-14","cited_by_count":281},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"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":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"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":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133},{"id":"1808.01097","title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","created":"2018-08-03","cited_by_count":126},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2006.15412","title":"Submodular Combinatorial Information Measures with Applications in Machine Learning","created":"2020-06-27","cited_by_count":88},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"2111.12621","title":"Accelerating Deep Learning with Dynamic Data Pruning","created":"2021-11-24","cited_by_count":43},{"id":"2006.05482","title":"Coresets for Near-Convex Functions","created":"2020-06-09","cited_by_count":38},{"id":"1602.02283","title":"Importance Sampling for Minibatches","created":"2016-02-06","cited_by_count":36},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23}],"next_cursor":null}