{"list":"other","total":57,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"1903.09291","title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","created":"2019-03-22","cited_by_count":146},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"2010.10732","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","created":"2020-10-21","cited_by_count":93},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78},{"id":"1805.08941","title":"AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference","created":"2018-05-23","cited_by_count":77},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77},{"id":"1904.12368","title":"Towards Efficient Model Compression via Learned Global Ranking","created":"2019-04-28","cited_by_count":75},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"2005.03354","title":"DMCP: Differentiable Markov Channel Pruning for Neural Networks","created":"2020-05-07","cited_by_count":69},{"id":"2203.01665","title":"$\\beta$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search","created":"2022-03-03","cited_by_count":64},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50},{"id":"1912.10952","title":"Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild","created":"2019-12-23","cited_by_count":40},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36},{"id":"1905.04748","title":"Approximated Oracle Filter Pruning for Destructive CNN Width Optimization","created":"2019-05-12","cited_by_count":35},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"2203.16172","title":"Self-Distillation from the Last Mini-Batch for Consistency Regularization","created":"2022-03-30","cited_by_count":29},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27},{"id":"2304.07018","title":"DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution","created":"2023-04-14","cited_by_count":19},{"id":"2007.03154","title":"Discretization-Aware Architecture Search","created":"2020-07-07","cited_by_count":14},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12},{"id":"2210.04153","title":"Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing","created":"2022-10-09","cited_by_count":10},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9},{"id":"2109.15014","title":"Deep Neural Compression Via Concurrent Pruning and Self-Distillation","created":"2021-09-30","cited_by_count":3},{"id":"2308.13772","title":"Boosting Residual Networks with Group Knowledge","created":"2023-08-26","cited_by_count":3},{"id":"2310.15115","title":"SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution","created":"2023-10-23","cited_by_count":2},{"id":"2403.06417","title":"Enhanced Sparsification via Stimulative Training","created":"2024-03-11","cited_by_count":2}],"next_cursor":null}