{"list":"other","total":89,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"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":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"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":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"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":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1908.03930","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","created":"2019-08-11","cited_by_count":178},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"1905.08114","title":"Zero-Shot Knowledge Distillation in Deep Networks","created":"2019-05-20","cited_by_count":121},{"id":"1707.01629","title":"Dual Path Networks","created":"2017-07-06","cited_by_count":119},{"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":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"1911.13053","title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","created":"2019-11-29","cited_by_count":81},{"id":"2007.02491","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","created":"2020-07-06","cited_by_count":80},{"id":"1812.08934","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","created":"2018-12-21","cited_by_count":76},{"id":"1804.07802","title":"Value-aware Quantization for Training and Inference of Neural Networks","created":"2018-04-20","cited_by_count":52},{"id":"1611.06440","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","created":"2016-11-19","cited_by_count":48},{"id":"1706.00388","title":"DiracNets: Training Very Deep Neural Networks Without Skip-Connections","created":"2017-06-01","cited_by_count":47},{"id":"1705.07283","title":"Structured Bayesian Pruning via Log-Normal Multiplicative Noise","created":"2017-05-20","cited_by_count":39},{"id":"2010.15821","title":"Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search","created":"2020-10-29","cited_by_count":38},{"id":"1610.09650","title":"Deep Model Compression: Distilling Knowledge from Noisy Teachers","created":"2016-10-30","cited_by_count":36},{"id":"2012.08859","title":"Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces","created":"2020-12-16","cited_by_count":32},{"id":"1911.09074","title":"Search to Distill: Pearls are Everywhere but not the Eyes","created":"2019-11-20","cited_by_count":26},{"id":"1912.07651","title":"UNAS: Differentiable Architecture Search Meets Reinforcement Learning","created":"2019-12-16","cited_by_count":21},{"id":"1811.08634","title":"Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs","created":"2018-11-21","cited_by_count":18},{"id":"1803.10750","title":"Adversarial Network Compression","created":"2018-03-28","cited_by_count":9}],"next_cursor":null}