{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"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":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"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":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"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":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1612.02295","title":"Large-Margin Softmax Loss for Convolutional Neural Networks","created":"2016-12-07","cited_by_count":296},{"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":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"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":"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":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"1804.00891","title":"Hyperspherical Variational Auto-Encoders","created":"2018-04-03","cited_by_count":189},{"id":"1711.11294","title":"Towards Accurate Binary Convolutional Neural Network","created":"2017-11-30","cited_by_count":149},{"id":"1909.13144","title":"Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks","created":"2019-09-28","cited_by_count":148},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"1609.01704","title":"Hierarchical Multiscale Recurrent Neural Networks","created":"2016-09-06","cited_by_count":104},{"id":"1907.05686","title":"And the Bit Goes Down: Revisiting the Quantization of Neural Networks","created":"2019-07-12","cited_by_count":78},{"id":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64},{"id":"1707.09870","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","created":"2017-07-24","cited_by_count":61},{"id":"1305.2982","title":"Estimating or Propagating Gradients Through Stochastic Neurons","created":"2013-05-14","cited_by_count":55},{"id":"1711.03189","title":"Deep Hyperspherical Learning","created":"2017-11-08","cited_by_count":55},{"id":"1711.02638","title":"Compression-aware Training of Deep Networks","created":"2017-11-07","cited_by_count":46},{"id":"1804.08071","title":"Decoupled Networks","created":"2018-04-22","cited_by_count":45},{"id":"2004.04690","title":"Orthogonal Over-Parameterized Training","created":"2020-04-09","cited_by_count":44},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31},{"id":"1710.07739","title":"Learning Discrete Weights Using the Local Reparameterization Trick","created":"2017-10-21","cited_by_count":29},{"id":"1912.02279","title":"Angular Visual Hardness","created":"2019-12-04","cited_by_count":29},{"id":"2010.15703","title":"Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks","created":"2020-10-29","cited_by_count":28},{"id":"1802.08530","title":"Training wide residual networks for deployment using a single bit for each weight","created":"2018-02-23","cited_by_count":10},{"id":"1912.02057","title":"RTN: Reparameterized Ternary Network","created":"2019-12-04","cited_by_count":9},{"id":"1707.04319","title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","created":"2017-07-13","cited_by_count":8},{"id":"2007.09818","title":"DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks","created":"2020-07-19","cited_by_count":8},{"id":"2008.05101","title":"FATNN: Fast and Accurate Ternary Neural Networks","created":"2020-08-12","cited_by_count":7},{"id":"1911.01028","title":"Ternary MobileNets via Per-Layer Hybrid Filter Banks","created":"2019-11-04","cited_by_count":3}],"next_cursor":null}