{"list":"other","total":51,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"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":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"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":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"1808.07576","title":"Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms","created":"2018-08-22","cited_by_count":106},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1603.05201","title":"Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units","created":"2016-03-16","cited_by_count":86},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"1611.03214","title":"Ultimate tensorization: compressing convolutional and FC layers alike","created":"2016-11-10","cited_by_count":56},{"id":"1810.07751","title":"Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems","created":"2018-09-28","cited_by_count":25},{"id":"1904.02698","title":"T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor","created":"2019-04-04","cited_by_count":22},{"id":"1806.00178","title":"IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks","created":"2018-06-01","cited_by_count":14},{"id":"1804.06202","title":"IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks","created":"2018-04-17","cited_by_count":12},{"id":"1807.11254","title":"Extreme Network Compression via Filter Group Approximation","created":"2018-07-30","cited_by_count":12},{"id":"2003.07469","title":"SlimConv: Reducing Channel Redundancy in Convolutional Neural Networks by Weights Flipping","created":"2020-03-16","cited_by_count":11},{"id":"1901.00366","title":"Learning Efficient Detector with Semi-supervised Adaptive Distillation","created":"2019-01-02","cited_by_count":10},{"id":"1702.04683","title":"Distributed deep learning on edge-devices: feasibility via adaptive compression","created":"2017-02-15","cited_by_count":5},{"id":"2002.07520","title":"Gradient $\\ell_1$ Regularization for Quantization Robustness","created":"2020-02-18","cited_by_count":4}],"next_cursor":null}