{"list":"other","total":82,"rows":[{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"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":"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"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":"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":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"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":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"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":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"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":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"1908.05033","title":"Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks","created":"2019-08-14","cited_by_count":238},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"1905.12322","title":"A Study of BFLOAT16 for Deep Learning Training","created":"2019-05-29","cited_by_count":232},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"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":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"1612.07119","title":"FINN: A Framework for Fast, Scalable Binarized Neural Network Inference","created":"2016-12-01","cited_by_count":150},{"id":"1711.11294","title":"Towards Accurate Binary Convolutional Neural Network","created":"2017-11-30","cited_by_count":149},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"1507.06149","title":"Data-free parameter pruning for Deep Neural Networks","created":"2015-07-22","cited_by_count":112},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"1602.02830","title":"Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1","created":"2016-02-09","cited_by_count":105},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1904.08444","title":"Defensive Quantization: When Efficiency Meets Robustness","created":"2019-04-17","cited_by_count":95},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"1803.04014","title":"NVIDIA Tensor Core Programmability, Performance & Precision","created":"2018-03-11","cited_by_count":79},{"id":"1711.00205","title":"Towards Effective Low-bitwidth Convolutional Neural Networks","created":"2017-11-01","cited_by_count":78},{"id":"1807.11205","title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes","created":"2018-07-30","cited_by_count":63},{"id":"1904.02823","title":"Regularizing Activation Distribution for Training Binarized Deep Networks","created":"2019-04-04","cited_by_count":61},{"id":"1810.00861","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","created":"2018-10-01","cited_by_count":59},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"1707.01220","title":"DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer","created":"2017-07-05","cited_by_count":56},{"id":"1809.04570","title":"FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks","created":"2018-09-12","cited_by_count":56},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"1802.00930","title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","created":"2018-02-03","cited_by_count":45},{"id":"1805.03718","title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks","created":"2018-05-09","cited_by_count":32},{"id":"1602.01517","title":"Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification","created":"2016-02-04","cited_by_count":29},{"id":"1904.00664","title":"Learning Content-Weighted Deep Image Compression","created":"2019-04-01","cited_by_count":28},{"id":"1910.10853","title":"Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation","created":"2019-10-24","cited_by_count":28},{"id":"1908.05858","title":"daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices","created":"2019-08-16","cited_by_count":27},{"id":"1807.00301","title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","created":"2018-07-01","cited_by_count":24},{"id":"1802.02733","title":"From Hashing to CNNs: Training BinaryWeight Networks via Hashing","created":"2018-02-08","cited_by_count":23},{"id":"1808.05240","title":"Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks","created":"2018-08-15","cited_by_count":21},{"id":"1909.11366","title":"Accurate and Compact Convolutional Neural Networks with Trained Binarization","created":"2019-09-25","cited_by_count":20},{"id":"1908.04680","title":"Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations","created":"2019-08-10","cited_by_count":18},{"id":"1909.12117","title":"Balanced Binary Neural Networks with Gated Residual","created":"2019-09-26","cited_by_count":14},{"id":"1705.09864","title":"BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet","created":"2017-05-27","cited_by_count":11},{"id":"1902.00730","title":"Self-Binarizing Networks","created":"2019-02-02","cited_by_count":11},{"id":"1606.05487","title":"YodaNN: An Architecture for Ultra-Low Power Binary-Weight CNN Acceleration","created":"2016-06-17","cited_by_count":7},{"id":"1808.04803","title":"Hierarchical binary CNNs for landmark localization with limited resources","created":"2018-08-14","cited_by_count":7},{"id":"1612.07625","title":"Hardware for Machine Learning: Challenges and Opportunities","created":"2016-12-22","cited_by_count":5},{"id":"1701.03400","title":"Scaling Binarized Neural Networks on Reconfigurable Logic","created":"2017-01-12","cited_by_count":4},{"id":"1810.02068","title":"Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA","created":"2018-10-04","cited_by_count":4},{"id":"1912.00286","title":"Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters","created":"2019-11-30","cited_by_count":3},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3},{"id":"1702.06392","title":"A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks","created":"2017-02-20","cited_by_count":2}],"next_cursor":null}