{"list":"other","total":75,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"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":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"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":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"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":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"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":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"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":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"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":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"1811.12817","title":"Practical Full Resolution Learned Lossless Image Compression","created":"2018-11-30","cited_by_count":94},{"id":"1903.08066","title":"Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks","created":"2019-03-19","cited_by_count":90},{"id":"1912.08881","title":"Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning","created":"2019-12-18","cited_by_count":89},{"id":"1907.05686","title":"And the Bit Goes Down: Revisiting the Quantization of Neural Networks","created":"2019-07-12","cited_by_count":78},{"id":"2001.00138","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","created":"2020-01-01","cited_by_count":76},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","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":"1810.00440","title":"Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters","created":"2018-09-30","cited_by_count":58},{"id":"1812.11677","title":"ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers","created":"2018-12-31","cited_by_count":42},{"id":"1711.02782","title":"Block-Sparse Recurrent Neural Networks","created":"2017-11-08","cited_by_count":39},{"id":"1705.08922","title":"Exploring the Regularity of Sparse Structure in Convolutional Neural Networks","created":"2017-05-24","cited_by_count":37},{"id":"2012.04643","title":"The Lottery Ticket Hypothesis for Object Recognition","created":"2020-12-08","cited_by_count":34},{"id":"1906.06624","title":"Scalable Model Compression by Entropy Penalized Reparameterization","created":"2019-06-15","cited_by_count":31},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"2007.15353","title":"Growing Efficient Deep Networks by Structured Continuous Sparsification","created":"2020-07-30","cited_by_count":28},{"id":"1807.09810","title":"Coreset-Based Neural Network Compression","created":"2018-07-25","cited_by_count":27},{"id":"1812.00353","title":"Accelerate CNN via Recursive Bayesian Pruning","created":"2018-12-02","cited_by_count":27},{"id":"2006.00896","title":"Pruning via Iterative Ranking of Sensitivity Statistics","created":"2020-06-01","cited_by_count":26},{"id":"1506.04449","title":"Compressing Convolutional Neural Networks","created":"2015-06-14","cited_by_count":25},{"id":"1807.00301","title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","created":"2018-07-01","cited_by_count":24},{"id":"1910.12708","title":"Evaluating Lottery Tickets Under Distributional Shifts","created":"2019-10-28","cited_by_count":23},{"id":"2005.03454","title":"Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture","created":"2020-05-04","cited_by_count":23},{"id":"2009.01174","title":"Transform Quantization for CNN (Convolutional Neural Network) Compression","created":"2020-09-02","cited_by_count":20},{"id":"2009.13270","title":"Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation","created":"2020-09-17","cited_by_count":8},{"id":"1905.08318","title":"DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression","created":"2019-05-15","cited_by_count":5}],"next_cursor":null}