{"list":"other","total":51,"rows":[{"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":"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"1709.05289","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","created":"2017-09-15","cited_by_count":179},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"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":"1611.00740","title":"Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review","created":"2016-11-02","cited_by_count":155},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2004.05565","title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","created":"2020-04-12","cited_by_count":152},{"id":"1511.06067","title":"Convolutional neural networks with low-rank regularization","created":"2015-11-19","cited_by_count":103},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"1312.6098","title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","created":"2013-12-20","cited_by_count":94},{"id":"1705.01714","title":"Optimal Approximation with Sparsely Connected Deep Neural Networks","created":"2017-05-04","cited_by_count":91},{"id":"1904.02877","title":"Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours","created":"2019-04-05","cited_by_count":87},{"id":"1610.04161","title":"Why Deep Neural Networks for Function Approximation?","created":"2016-10-13","cited_by_count":82},{"id":"1610.09887","title":"Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks","created":"2016-10-31","cited_by_count":59},{"id":"1612.07771","title":"Highway and Residual Networks learn Unrolled Iterative Estimation","created":"2016-12-22","cited_by_count":52},{"id":"2103.01396","title":"DeepReDuce: ReLU Reduction for Fast Private Inference","created":"2021-03-02","cited_by_count":50},{"id":"1702.08489","title":"Depth Separation for Neural Networks","created":"2017-02-27","cited_by_count":46},{"id":"2006.08733","title":"CryptoNAS: Private Inference on a ReLU Budget","created":"2020-06-15","cited_by_count":40},{"id":"1912.10178","title":"DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration","created":"2019-12-21","cited_by_count":24},{"id":"2009.04759","title":"Activate or Not: Learning Customized Activation","created":"2020-09-10","cited_by_count":22},{"id":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","cited_by_count":21},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20},{"id":"2003.12128","title":"Going in circles is the way forward: the role of recurrence in visual inference","created":"2020-03-26","cited_by_count":19},{"id":"2011.14356","title":"Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks","created":"2020-11-29","cited_by_count":18},{"id":"2007.14917","title":"Compressing Deep Neural Networks via Layer Fusion","created":"2020-07-29","cited_by_count":4}],"next_cursor":null}