{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"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":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"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":"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":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1410.0759","title":"cuDNN: Efficient Primitives for Deep Learning","created":"2014-10-03","cited_by_count":245},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"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":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"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":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"2007.02491","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","created":"2020-07-06","cited_by_count":80},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"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":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","cited_by_count":73},{"id":"1611.06321","title":"Learning the Number of Neurons in Deep Networks","created":"2016-11-19","cited_by_count":69},{"id":"2005.03354","title":"DMCP: Differentiable Markov Channel Pruning for Neural Networks","created":"2020-05-07","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":"1711.02017","title":"NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm","created":"2017-11-06","cited_by_count":60},{"id":"1906.00586","title":"Discovering Neural Wirings","created":"2019-06-03","cited_by_count":56},{"id":"2004.02164","title":"DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation","created":"2020-04-05","cited_by_count":47},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45},{"id":"1901.09290","title":"PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration","created":"2019-01-26","cited_by_count":41},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","cited_by_count":38},{"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":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2007.15353","title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","created":"2020-07-30","cited_by_count":28},{"id":"2106.09857","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods","created":"2021-06-18","cited_by_count":26},{"id":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14},{"id":"2401.00850","title":"Refining Pre-Trained Motion Models","created":"2024-01-01","cited_by_count":12},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11},{"id":"1410.4604","title":"Domain-Independent Optimistic Initialization for Reinforcement Learning","created":"2014-10-16","cited_by_count":8},{"id":"2109.04660","title":"Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights","created":"2021-09-10","cited_by_count":4},{"id":"2308.01905","title":"Revisiting Deformable Convolution for Depth Completion","created":"2023-08-03","cited_by_count":4},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4},{"id":"2306.13237","title":"Pruning for Better Domain Generalizability","created":"2023-06-22","cited_by_count":2}],"next_cursor":null}