{"list":"other","total":85,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"1912.10557","title":"Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing","created":"2019-12-22","cited_by_count":421},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1802.03690","title":"On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups","created":"2018-02-11","cited_by_count":300},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"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":"1802.05637","title":"cGANs with Projection Discriminator","created":"2018-02-15","cited_by_count":254},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"1809.00916","title":"OCNet: Object Context Network for Scene Parsing","created":"2018-09-04","cited_by_count":140},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"1910.12027","title":"Consistency Regularization for Generative Adversarial Networks","created":"2019-10-26","cited_by_count":136},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1906.02762","title":"Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View","created":"2019-06-06","cited_by_count":113},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"1909.12057","title":"B-Spline CNNs on Lie Groups","created":"2019-09-26","cited_by_count":97},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2002.03830","title":"Attentive Group Equivariant Convolutional Networks","created":"2020-02-07","cited_by_count":63},{"id":"2010.00977","title":"Group Equivariant Stand-Alone Self-Attention For Vision","created":"2020-10-02","cited_by_count":63},{"id":"1909.03402","title":"Squeeze-and-Attention Networks for Semantic Segmentation","created":"2019-09-08","cited_by_count":61},{"id":"1410.0342","title":"Generalized Low Rank Models","created":"2014-10-01","cited_by_count":55},{"id":"1903.02271","title":"High-Fidelity Image Generation With Fewer Labels","created":"2019-03-06","cited_by_count":52},{"id":"2003.10211","title":"Spatial Pyramid Based Graph Reasoning for Semantic Segmentation","created":"2020-03-23","cited_by_count":47},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"1912.00953","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","created":"2019-12-02","cited_by_count":42},{"id":"2007.10408","title":"PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions","created":"2020-07-20","cited_by_count":34},{"id":"1905.11634","title":"LatentGNN: Learning Efficient Non-local Relations for Visual Recognition","created":"2019-05-28","cited_by_count":25},{"id":"1911.12287","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","created":"2019-11-27","cited_by_count":21},{"id":"1404.7306","title":"Generalized Nonconvex Nonsmooth Low-Rank Minimization","created":"2014-04-29","cited_by_count":14},{"id":"2006.06147","title":"Implicit Kernel Attention","created":"2020-06-11","cited_by_count":13},{"id":"1806.00681","title":"Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling","created":"2018-06-02","cited_by_count":10},{"id":"1906.07671","title":"ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition","created":"2019-06-18","cited_by_count":9},{"id":"1912.00835","title":"Low Rank Factorization for Compact Multi-Head Self-Attention","created":"2019-11-26","cited_by_count":3}],"next_cursor":null}