{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1909.11480","title":"Input complexity and out-of-distribution detection with likelihood-based generative models","created":"2019-09-25","cited_by_count":186},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"1512.08571","title":"Structured Pruning of Deep Convolutional Neural Networks","created":"2015-12-29","cited_by_count":149},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"1911.09723","title":"Fast Sparse ConvNets","created":"2019-11-21","cited_by_count":86},{"id":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73},{"id":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"1912.05533","title":"SpecAugment on Large Scale Datasets","created":"2019-12-11","cited_by_count":60},{"id":"1908.08932","title":"Learning Filter Basis for Convolutional Neural Network Compression","created":"2019-08-23","cited_by_count":57},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43},{"id":"2006.00896","title":"Pruning via Iterative Ranking of Sensitivity Statistics","created":"2020-06-01","cited_by_count":26},{"id":"1802.06367","title":"Efficient Sparse-Winograd Convolutional Neural Networks","created":"2018-02-18","cited_by_count":20},{"id":"2004.09179","title":"GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples","created":"2020-04-20","cited_by_count":18},{"id":"2010.11354","title":"PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data","created":"2020-10-22","cited_by_count":17},{"id":"2012.00596","title":"NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration","created":"2020-12-01","cited_by_count":16},{"id":"2011.14087","title":"FreezeNet: Full Performance by Reduced Storage Costs","created":"2020-11-28","cited_by_count":13},{"id":"2202.03967","title":"Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration","created":"2022-02-08","cited_by_count":7},{"id":"2004.09166","title":"Invariant Integration in Deep Convolutional Feature Space","created":"2020-04-20","cited_by_count":6},{"id":"2107.12673","title":"COPS: Controlled Pruning Before Training Starts","created":"2021-07-27","cited_by_count":6}],"next_cursor":null}