{"list":"other","total":158,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"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":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"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":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"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":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"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":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1711.00436","title":"Hierarchical Representations for Efficient Architecture Search","created":"2017-11-01","cited_by_count":191},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2004.01803","title":"SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation","created":"2020-04-03","cited_by_count":170},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"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":"1804.09081","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","created":"2018-04-24","cited_by_count":153},{"id":"2004.05565","title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","created":"2020-04-12","cited_by_count":152},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"2008.10937","title":"A Survey on Evolutionary Neural Architecture Search","created":"2020-08-25","cited_by_count":142},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1904.01569","title":"Exploring Randomly Wired Neural Networks for Image Recognition","created":"2019-04-02","cited_by_count":103},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"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":"2109.10964","title":"Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces","created":"2021-09-22","cited_by_count":87},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","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":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"1810.00736","title":"Benchmark Analysis of Representative Deep Neural Network Architectures","created":"2018-10-01","cited_by_count":77},{"id":"1812.08934","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","created":"2018-12-21","cited_by_count":76},{"id":"1912.10917","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","created":"2019-12-23","cited_by_count":73},{"id":"2102.01063","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","created":"2021-02-01","cited_by_count":73},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"1803.10615","title":"SqueezeNext: Hardware-Aware Neural Network Design","created":"2018-03-23","cited_by_count":61},{"id":"2002.04809","title":"Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning","created":"2020-02-12","cited_by_count":61},{"id":"2003.13683","title":"DHP: Differentiable Meta Pruning via HyperNetworks","created":"2020-03-30","cited_by_count":57},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56},{"id":"2004.14525","title":"MobileDets: Searching for Object Detection Architectures for Mobile Accelerators","created":"2020-04-30","cited_by_count":55},{"id":"1905.12107","title":"SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers","created":"2019-05-28","cited_by_count":52},{"id":"1906.09607","title":"Densely Connected Search Space for More Flexible Neural Architecture Search","created":"2019-06-23","cited_by_count":52},{"id":"1907.03141","title":"AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates","created":"2019-07-06","cited_by_count":49},{"id":"1806.02639","title":"Path-Level Network Transformation for Efficient Architecture Search","created":"2018-06-07","cited_by_count":44},{"id":"1806.08198","title":"DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures","created":"2018-06-21","cited_by_count":40},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"2104.04382","title":"CondenseNet V2: Sparse Feature Reactivation for Deep Networks","created":"2021-04-09","cited_by_count":34},{"id":"1712.05134","title":"Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition","created":"2017-12-14","cited_by_count":33},{"id":"1605.06489","title":"Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups","created":"2016-05-20","cited_by_count":32},{"id":"2007.10026","title":"Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization","created":"2020-07-20","cited_by_count":32},{"id":"2012.08859","title":"Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces","created":"2020-12-16","cited_by_count":32},{"id":"1701.07148","title":"CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression","created":"2017-01-25","cited_by_count":30},{"id":"1905.10478","title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection","created":"2019-05-24","cited_by_count":26},{"id":"1911.09074","title":"Search to Distill: Pearls are Everywhere but not the Eyes","created":"2019-11-20","cited_by_count":26}],"next_cursor":"100"}