{"list":"other","total":71,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2202.11214","title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","created":"2022-02-22","cited_by_count":776},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2104.00954","title":"Skillful Precipitation Nowcasting using Deep Generative Models of Radar","created":"2021-04-02","cited_by_count":311},{"id":"1807.03247","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","created":"2018-07-09","cited_by_count":307},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"2002.00469","title":"WeatherBench: A benchmark dataset for data-driven weather forecasting","created":"2020-02-02","cited_by_count":275},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"1706.03458","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","created":"2017-06-12","cited_by_count":182},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175},{"id":"2202.07575","title":"Forecasting Global Weather with Graph Neural Networks","created":"2022-02-15","cited_by_count":168},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"1810.05148","title":"Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes","created":"2018-10-11","cited_by_count":167},{"id":"2003.12140","title":"MetNet: A Neural Weather Model for Precipitation Forecasting","created":"2020-03-24","cited_by_count":131},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"1601.04589","title":"Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis","created":"2016-01-18","cited_by_count":102},{"id":"1805.09091","title":"Neural networks for post-processing ensemble weather forecasts","created":"2018-05-23","cited_by_count":95},{"id":"1305.0445","title":"Deep Learning of Representations: Looking Forward","created":"2013-05-02","cited_by_count":84},{"id":"1804.02391","title":"Learn To Pay Attention","created":"2018-04-06","cited_by_count":83},{"id":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","cited_by_count":73},{"id":"1704.06363","title":"Hard Mixtures of Experts for Large Scale Weakly Supervised Vision","created":"2017-04-20","cited_by_count":67},{"id":"1912.12132","title":"Machine Learning for Precipitation Nowcasting from Radar Images","created":"2019-12-11","cited_by_count":56},{"id":"1604.06119","title":"Network of Experts for Large-Scale Image Categorization","created":"2016-04-20","cited_by_count":54},{"id":"2005.08748","title":"Deep Learning for Post-Processing Ensemble Weather Forecasts","created":"2020-05-18","cited_by_count":52},{"id":"1811.11205","title":"You Look Twice: GaterNet for Dynamic Filter Selection in CNNs","created":"2018-11-27","cited_by_count":46},{"id":"1903.11257","title":"How Can We Be So Dense? The Benefits of Using Highly Sparse Representations","created":"2019-03-27","cited_by_count":45},{"id":"1312.4461","title":"Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networks","created":"2013-12-16","cited_by_count":44},{"id":"1703.06217","title":"Deciding How to Decide: Dynamic Routing in Artificial Neural Networks","created":"2017-03-17","cited_by_count":33},{"id":"2002.02959","title":"Revisiting Spatial Invariance with Low-Rank Local Connectivity","created":"2020-02-07","cited_by_count":29},{"id":"2007.00864","title":"Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights","created":"2020-07-02","cited_by_count":28},{"id":"1606.07230","title":"Deep Learning Markov Random Field for Semantic Segmentation","created":"2016-06-23","cited_by_count":27},{"id":"1905.11634","title":"LatentGNN: Learning Efficient Non-local Relations for Visual Recognition","created":"2019-05-28","cited_by_count":25},{"id":"1406.7362","title":"Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning","created":"2014-06-28","cited_by_count":24},{"id":"2008.09662","title":"Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations","created":"2020-08-21","cited_by_count":20},{"id":"2111.07470","title":"Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks","created":"2021-11-14","cited_by_count":20},{"id":"1511.07838","title":"Dynamic Capacity Networks","created":"2015-11-24","cited_by_count":16},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15},{"id":"2206.14786","title":"ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts","created":"2022-06-29","cited_by_count":13},{"id":"1410.0510","title":"Deep Sequential Neural Network","created":"2014-10-02","cited_by_count":7}],"next_cursor":null}