{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"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":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1802.00124","title":"Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers","created":"2018-02-01","cited_by_count":112},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"2007.03260","title":"ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting","created":"2020-07-07","cited_by_count":85},{"id":"1904.03837","title":"Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure","created":"2019-04-08","cited_by_count":76},{"id":"1909.12778","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","created":"2019-09-27","cited_by_count":70},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","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":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36},{"id":"2206.06662","title":"Learning Best Combination for Efficient N:M Sparsity","created":"2022-06-14","cited_by_count":32},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27},{"id":"2104.11883","title":"Carrying out CNN Channel Pruning in a White Box","created":"2021-04-24","cited_by_count":22},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20},{"id":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16},{"id":"1811.08390","title":"Structured Pruning for Efficient ConvNets via Incremental Regularization","created":"2018-11-20","cited_by_count":15},{"id":"1904.03961","title":"Filter Pruning by Switching to Neighboring CNNs with Good Attributes","created":"2019-04-08","cited_by_count":15},{"id":"1908.03888","title":"HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions","created":"2019-08-11","cited_by_count":13},{"id":"2304.14636","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","created":"2023-04-28","cited_by_count":11},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9},{"id":"2107.06916","title":"Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion","created":"2021-07-14","cited_by_count":5},{"id":"2210.16589","title":"Strong Lottery Ticket Hypothesis with $\\varepsilon$--perturbation","created":"2022-10-29","cited_by_count":3},{"id":"2409.14633","title":"Hierarchical end-to-end autonomous navigation through few-shot waypoint detection","created":"2024-09-23","cited_by_count":3}],"next_cursor":null}