{"list":"other","total":78,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"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":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"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":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"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":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"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":"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":"2004.09576","title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","created":"2020-04-20","cited_by_count":189},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1811.09716","title":"Robustness via curvature regularization, and vice versa","created":"2018-11-23","cited_by_count":175},{"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":"1911.09464","title":"Quantization Networks","created":"2019-11-21","cited_by_count":153},{"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":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"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":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"1708.00107","title":"Learned in Translation: Contextualized Word Vectors","created":"2017-08-01","cited_by_count":104},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87},{"id":"2004.05795","title":"Rethinking Differentiable Search for Mixed-Precision Neural Networks","created":"2020-04-13","cited_by_count":82},{"id":"1711.00205","title":"Towards Effective Low-bitwidth Convolutional Neural Networks","created":"2017-11-01","cited_by_count":78},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","cited_by_count":78},{"id":"1912.09666","title":"AdaBits: Neural Network Quantization with Adaptive Bit-Widths","created":"2019-12-20","cited_by_count":64},{"id":"1904.02823","title":"Regularizing Activation Distribution for Training Binarized Deep Networks","created":"2019-04-04","cited_by_count":61},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61},{"id":"2011.10680","title":"HAWQV3: Dyadic Neural Network Quantization","created":"2020-11-20","cited_by_count":60},{"id":"2006.08403","title":"On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them","created":"2020-06-15","cited_by_count":59},{"id":"2008.04693","title":"PROFIT: A Novel Training Method for sub-4-bit MobileNet Models","created":"2020-08-11","cited_by_count":50},{"id":"2007.10463","title":"Differentiable Joint Pruning and Quantization for Hardware Efficiency","created":"2020-07-20","cited_by_count":46},{"id":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45},{"id":"2103.07156","title":"Learnable Companding Quantization for Accurate Low-bit Neural Networks","created":"2021-03-12","cited_by_count":42},{"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":"2007.07197","title":"Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search","created":"2020-07-07","cited_by_count":33},{"id":"2001.05936","title":"MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?","created":"2020-01-16","cited_by_count":32},{"id":"1802.08635","title":"Loss-aware Weight Quantization of Deep Networks","created":"2018-02-23","cited_by_count":31},{"id":"1912.08883","title":"Adaptive Loss-aware Quantization for Multi-bit Networks","created":"2019-12-18","cited_by_count":30},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19},{"id":"2108.02720","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","created":"2021-08-05","cited_by_count":11},{"id":"2007.06919","title":"AQD: Towards Accurate Fully-Quantized Object Detection","created":"2020-07-14","cited_by_count":5},{"id":"2103.00219","title":"Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets","created":"2021-02-27","cited_by_count":3}],"next_cursor":null}