{"list":"other","total":103,"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":"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"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":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"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":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"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":"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":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"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":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"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":"2004.12088","title":"SplitFed: When Federated Learning Meets Split Learning","created":"2020-04-25","cited_by_count":310},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1905.12322","title":"A Study of BFLOAT16 for Deep Learning Training","created":"2019-05-29","cited_by_count":232},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"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":"1911.09464","title":"Quantization Networks","created":"2019-11-21","cited_by_count":153},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"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":"1708.04485","title":"SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks","created":"2017-05-23","cited_by_count":135},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1810.05331","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","created":"2018-10-12","cited_by_count":129},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1709.01921","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","created":"2017-09-06","cited_by_count":120},{"id":"1803.04311","title":"Deep Learning in Mobile and Wireless Networking: A Survey","created":"2018-03-12","cited_by_count":118},{"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":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"1712.01507","title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks","created":"2017-12-05","cited_by_count":109},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1509.09308","title":"Fast Algorithms for Convolutional Neural Networks","created":"2015-09-30","cited_by_count":102},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"1705.06963","title":"A Survey of Neuromorphic Computing and Neural Networks in Hardware","created":"2017-05-19","cited_by_count":85},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"1810.10090","title":"NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision","created":"2018-10-23","cited_by_count":68},{"id":"1509.08971","title":"Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition","created":"2015-09-29","cited_by_count":67},{"id":"1803.10615","title":"SqueezeNext: Hardware-Aware Neural Network Design","created":"2018-03-23","cited_by_count":61},{"id":"1912.03413","title":"Dissecting the Graphcore IPU Architecture via Microbenchmarking","created":"2019-12-07","cited_by_count":47},{"id":"1711.02213","title":"Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks","created":"2017-11-06","cited_by_count":44},{"id":"1804.01526","title":"Training DNNs with Hybrid Block Floating Point","created":"2018-04-04","cited_by_count":40},{"id":"1706.01406","title":"NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps","created":"2017-06-05","cited_by_count":39},{"id":"1705.01626","title":"Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks","created":"2017-05-03","cited_by_count":37},{"id":"1909.02384","title":"Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers","created":"2019-09-05","cited_by_count":33},{"id":"1603.07341","title":"Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices","created":"2016-03-23","cited_by_count":29},{"id":"1412.7580","title":"Fast Convolutional Nets With fbfft: A GPU Performance Evaluation","created":"2014-12-24","cited_by_count":27},{"id":"1811.09332","title":"Structured Pruning of Neural Networks with Budget-Aware Regularization","created":"2018-11-23","cited_by_count":26},{"id":"1511.05077","title":"Diversity Networks: Neural Network Compression Using Determinantal Point Processes","created":"2015-11-16","cited_by_count":25},{"id":"1804.06508","title":"UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition","created":"2018-04-18","cited_by_count":20},{"id":"1612.03940","title":"Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks","created":"2016-12-12","cited_by_count":18},{"id":"1705.08014","title":"Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices","created":"2017-05-22","cited_by_count":18},{"id":"2105.03596","title":"Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms","created":"2021-05-08","cited_by_count":18},{"id":"1811.06992","title":"Image Classification at Supercomputer Scale","created":"2018-11-16","cited_by_count":16},{"id":"1812.01762","title":"Deep Positron: A Deep Neural Network Using the Posit Number System","created":"2018-12-05","cited_by_count":13},{"id":"2111.01956","title":"One Pass ImageNet","created":"2021-11-03","cited_by_count":11},{"id":"2108.10147","title":"Spatio-Temporal Split Learning for Privacy-Preserving Medical Platforms: Case Studies with COVID-19 CT, X-Ray, and Cholesterol Data","created":"2021-08-20","cited_by_count":10},{"id":"1601.06815","title":"Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add","created":"2016-01-25","cited_by_count":7},{"id":"1802.03750","title":"FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy","created":"2018-02-11","cited_by_count":7},{"id":"1903.10584","title":"Performance-Efficiency Trade-off of Low-Precision Numerical Formats in Deep Neural Networks","created":"2019-03-25","cited_by_count":7},{"id":"1909.04509","title":"Unrolling Ternary Neural Networks","created":"2019-09-09","cited_by_count":7},{"id":"1909.10818","title":"Constrained deep neural network architecture search for IoT devices accounting hardware calibration","created":"2019-09-24","cited_by_count":6},{"id":"2010.00704","title":"BCNN: A Binary CNN with All Matrix Ops Quantized to 1 Bit Precision","created":"2020-10-01","cited_by_count":6},{"id":"2007.12216","title":"Efficient Residue Number System Based Winograd Convolution","created":"2020-07-23","cited_by_count":5},{"id":"1807.01356","title":"Efficient ConvNets for Analog Arrays","created":"2018-07-03","cited_by_count":4}],"next_cursor":"100"}