{"list":"other","total":63,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"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":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"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":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"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":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1408.5093","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","created":"2014-06-20","cited_by_count":288},{"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":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"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":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"1808.05779","title":"Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss","created":"2018-08-17","cited_by_count":160},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"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":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1603.01025","title":"Convolutional Neural Networks using Logarithmic Data Representation","created":"2016-03-03","cited_by_count":99},{"id":"1902.01996","title":"Are All Layers Created Equal?","created":"2019-02-06","cited_by_count":94},{"id":"1711.00205","title":"Towards Effective Low-bitwidth Convolutional Neural Networks","created":"2017-11-01","cited_by_count":78},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"1612.01051","title":"SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving","created":"2016-12-04","cited_by_count":55},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"2008.04693","title":"PROFIT: A Novel Training Method for sub-4-bit MobileNet Models","created":"2020-08-11","cited_by_count":50},{"id":"1902.01917","title":"Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization","created":"2019-02-05","cited_by_count":45},{"id":"1810.05723","title":"Post-training 4-bit quantization of convolution networks for rapid-deployment","created":"2018-10-02","cited_by_count":42},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"1905.13082","title":"Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers","created":"2019-05-30","cited_by_count":33},{"id":"1802.08635","title":"Loss-aware Weight Quantization of Deep Networks","created":"2018-02-23","cited_by_count":31},{"id":"1901.00121","title":"FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review","created":"2019-01-01","cited_by_count":29},{"id":"1807.00301","title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","created":"2018-07-01","cited_by_count":24},{"id":"1806.08862","title":"BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing","created":"2018-06-22","cited_by_count":22},{"id":"1706.07145","title":"Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks","created":"2017-06-22","cited_by_count":21},{"id":"1810.05488","title":"Quantization for Rapid Deployment of Deep Neural Networks","created":"2018-10-12","cited_by_count":20},{"id":"1807.06964","title":"Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)","created":"2018-07-17","cited_by_count":19},{"id":"1705.01462","title":"Ternary Neural Networks with Fine-Grained Quantization","created":"2017-05-02","cited_by_count":17},{"id":"2006.09049","title":"Multi-Precision Policy Enforced Training (MuPPET): A precision-switching strategy for quantised fixed-point training of CNNs","created":"2020-06-16","cited_by_count":11},{"id":"1811.01907","title":"A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM","created":"2018-11-05","cited_by_count":10},{"id":"2008.04878","title":"Hardware-Centric AutoML for Mixed-Precision Quantization","created":"2020-08-11","cited_by_count":8},{"id":"1807.05053","title":"CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks","created":"2018-07-13","cited_by_count":5},{"id":"1812.01965","title":"Training Competitive Binary Neural Networks from Scratch","created":"2018-12-05","cited_by_count":4},{"id":"1702.08231","title":"Low-Precision Batch-Normalized Activations","created":"2017-02-27","cited_by_count":3},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2}],"next_cursor":null}