{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"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":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"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":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"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":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1908.05033","title":"Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks","created":"2019-08-14","cited_by_count":238},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"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":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1911.09464","title":"Quantization Networks","created":"2019-11-21","cited_by_count":153},{"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":"2005.03842","title":"GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference","created":"2020-05-08","cited_by_count":106},{"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":"1906.07538","title":"Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection","created":"2019-06-18","cited_by_count":73},{"id":"1712.01048","title":"Adaptive Quantization for Deep Neural Network","created":"2017-12-04","cited_by_count":67},{"id":"2002.07686","title":"Robust Quantization: One Model to Rule Them All","created":"2020-02-18","cited_by_count":63},{"id":"1904.10631","title":"Low-Memory Neural Network Training: A Technical Report","created":"2019-04-24","cited_by_count":57},{"id":"2003.12783","title":"CNN-based Density Estimation and Crowd Counting: A Survey","created":"2020-03-28","cited_by_count":43},{"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":"1810.00162","title":"NICE: Noise Injection and Clamping Estimation for Neural Network Quantization","created":"2018-09-29","cited_by_count":24},{"id":"2002.06517","title":"BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations","created":"2020-02-16","cited_by_count":23},{"id":"1806.08862","title":"BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing","created":"2018-06-22","cited_by_count":22},{"id":"1705.01462","title":"Ternary Neural Networks with Fine-Grained Quantization","created":"2017-05-02","cited_by_count":17},{"id":"1712.08934","title":"A Survey of FPGA-Based Neural Network Accelerator","created":"2017-12-24","cited_by_count":17},{"id":"1912.10207","title":"Towards Efficient Training for Neural Network Quantization","created":"2019-12-21","cited_by_count":16},{"id":"1910.04877","title":"Bit Efficient Quantization for Deep Neural Networks","created":"2019-10-07","cited_by_count":14},{"id":"1805.08691","title":"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe","created":"2018-05-04","cited_by_count":5},{"id":"2002.07136","title":"Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations","created":"2020-02-17","cited_by_count":5},{"id":"1908.07748","title":"RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs","created":"2019-08-21","cited_by_count":4},{"id":"2012.12775","title":"Adaptive Precision Training for Resource Constrained Devices","created":"2020-12-23","cited_by_count":2}],"next_cursor":null}