{"list":"other","total":62,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2010.07611","title":"Layer-adaptive sparsity for the Magnitude-based Pruning","created":"2020-10-15","cited_by_count":126},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"1505.06798","title":"Accelerating Very Deep Convolutional Networks for Classification and Detection","created":"2015-05-26","cited_by_count":109},{"id":"1511.06067","title":"Convolutional neural networks with low-rank regularization","created":"2015-11-19","cited_by_count":103},{"id":"2007.02491","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","created":"2020-07-06","cited_by_count":80},{"id":"1909.12778","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","created":"2019-09-27","cited_by_count":70},{"id":"1611.06321","title":"Learning the Number of Neurons in Deep Networks","created":"2016-11-19","cited_by_count":69},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"1607.00345","title":"Convergence Rate of Frank-Wolfe for Non-Convex Objectives","created":"2016-07-01","cited_by_count":63},{"id":"1803.01814","title":"Norm matters: efficient and accurate normalization schemes in deep networks","created":"2018-03-05","cited_by_count":62},{"id":"1906.00586","title":"Discovering Neural Wirings","created":"2019-06-03","cited_by_count":56},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2004.09031","title":"Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification","created":"2020-04-20","cited_by_count":53},{"id":"1711.02638","title":"Compression-aware Training of Deep Networks","created":"2017-11-07","cited_by_count":46},{"id":"1607.08254","title":"Stochastic Frank-Wolfe Methods for Nonconvex Optimization","created":"2016-07-27","cited_by_count":41},{"id":"1602.02101","title":"Variance-Reduced and Projection-Free Stochastic Optimization","created":"2016-02-05","cited_by_count":40},{"id":"1905.04753","title":"Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints","created":"2019-05-12","cited_by_count":37},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33},{"id":"2004.14566","title":"TRP: Trained Rank Pruning for Efficient Deep Neural Networks","created":"2020-04-30","cited_by_count":32},{"id":"1802.08183","title":"Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity","created":"2018-02-22","cited_by_count":31},{"id":"2007.15353","title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","created":"2020-07-30","cited_by_count":28},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25},{"id":"1703.09746","title":"Coordinating Filters for Faster Deep Neural Networks","created":"2017-03-28","cited_by_count":24},{"id":"2010.07243","title":"Deep Neural Network Training with Frank-Wolfe","created":"2020-10-14","cited_by_count":23},{"id":"1607.03463","title":"LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain","created":"2016-07-12","cited_by_count":22},{"id":"1711.01660","title":"Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap","created":"2017-11-05","cited_by_count":21},{"id":"2101.10040","title":"Complexity of Linear Minimization and Projection on Some Sets","created":"2021-01-25","cited_by_count":20},{"id":"1910.09396","title":"Efficient Projection-Free Online Methods with Stochastic Recursive Gradient","created":"2019-10-21","cited_by_count":19},{"id":"2002.11860","title":"Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization","created":"2020-02-27","cited_by_count":14},{"id":"2111.00843","title":"How I Learned to Stop Worrying and Love Retraining","created":"2021-11-01","cited_by_count":12},{"id":"1811.07591","title":"Deep Frank-Wolfe For Neural Network Optimization","created":"2018-11-19","cited_by_count":11},{"id":"1803.06453","title":"Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision","created":"2018-03-17","cited_by_count":7},{"id":"2009.14114","title":"Projection-Free Adaptive Gradients for Large-Scale Optimization","created":"2020-09-29","cited_by_count":6},{"id":"1510.07169","title":"Fast and Scalable Lasso via Stochastic Frank-Wolfe Methods with a Convergence Guarantee","created":"2015-10-24","cited_by_count":5},{"id":"1601.00449","title":"Fitting Spectral Decay with the $k$-Support Norm","created":"2016-01-04","cited_by_count":3},{"id":"1906.03580","title":"Stochastic In-Face Frank-Wolfe Methods for Non-Convex Optimization and Sparse Neural Network Training","created":"2019-06-09","cited_by_count":3}],"next_cursor":null}