{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"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":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"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":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"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":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"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":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"1603.07285","title":"A guide to convolution arithmetic for deep learning","created":"2016-03-23","cited_by_count":185},{"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":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"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":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"2002.00104","title":"Post-Training Piecewise Linear Quantization for Deep Neural Networks","created":"2020-01-31","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":"1804.07802","title":"Value-aware Quantization for Training and Inference of Neural Networks","created":"2018-04-20","cited_by_count":52},{"id":"1802.00930","title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","created":"2018-02-03","cited_by_count":45},{"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":"1811.10413","title":"Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation","created":"2018-11-22","cited_by_count":37},{"id":"1903.11236","title":"Training Quantized Neural Networks with a Full-precision Auxiliary Module","created":"2019-03-27","cited_by_count":35},{"id":"1610.06920","title":"Bit-pragmatic Deep Neural Network Computing","created":"2016-10-20","cited_by_count":32},{"id":"1805.03718","title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks","created":"2018-05-09","cited_by_count":32},{"id":"2001.00705","title":"Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference","created":"2020-01-03","cited_by_count":23},{"id":"2001.05674","title":"Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks","created":"2020-01-16","cited_by_count":23},{"id":"1803.08607","title":"A Quantization-Friendly Separable Convolution for MobileNets","created":"2018-03-22","cited_by_count":22},{"id":"1811.01721","title":"Rethinking floating point for deep learning","created":"2018-11-01","cited_by_count":22},{"id":"1803.03383","title":"High-Accuracy Low-Precision Training","created":"2018-03-09","cited_by_count":20},{"id":"1810.05488","title":"Quantization for Rapid Deployment of Deep Neural Networks","created":"2018-10-12","cited_by_count":20},{"id":"1706.07853","title":"Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks","created":"2017-06-23","cited_by_count":12},{"id":"1806.01107","title":"GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks","created":"2018-05-10","cited_by_count":11},{"id":"1602.04183","title":"Dark Memory and Accelerator-Rich System Optimization in the Dark Silicon Era","created":"2016-02-12","cited_by_count":9},{"id":"1610.00324","title":"Accelerating Deep Convolutional Networks using low-precision and sparsity","created":"2016-10-02","cited_by_count":8},{"id":"1909.03831","title":"Training Deep Neural Networks Using Posit Number System","created":"2019-09-06","cited_by_count":6},{"id":"1909.13271","title":"AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference","created":"2019-09-29","cited_by_count":5},{"id":"1912.12656","title":"Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection","created":"2019-12-29","cited_by_count":5},{"id":"1803.03688","title":"Bit-Tactical: Exploiting Ineffectual Computations in Convolutional Neural Networks: Which, Why, and How","created":"2018-03-09","cited_by_count":2}],"next_cursor":null}