{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"1802.08139","title":"Path-Specific Counterfactual Fairness","created":"2018-02-22","cited_by_count":181},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"1811.11553","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","created":"2018-11-28","cited_by_count":143},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"1704.08509","title":"No More Discrimination: Cross City Adaptation of Road Scene Segmenters","created":"2017-04-27","cited_by_count":111},{"id":"1906.03292","title":"On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset","created":"2019-06-07","cited_by_count":100},{"id":"1906.06439","title":"Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias","created":"2019-06-14","cited_by_count":74},{"id":"1804.01118","title":"Synthesizing Programs for Images using Reinforced Adversarial Learning","created":"2018-04-03","cited_by_count":72},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57},{"id":"2003.04490","title":"Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion","created":"2020-03-10","cited_by_count":47},{"id":"1810.02513","title":"Learning To Simulate","created":"2018-10-05","cited_by_count":44},{"id":"2106.03734","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","created":"2021-06-07","cited_by_count":43},{"id":"2005.10430","title":"Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation","created":"2020-05-21","cited_by_count":37},{"id":"1904.05916","title":"Synthetic Examples Improve Generalization for Rare Classes","created":"2019-04-11","cited_by_count":35},{"id":"2108.05305","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","created":"2021-08-11","cited_by_count":35},{"id":"1712.01619","title":"Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems","created":"2017-12-05","cited_by_count":28},{"id":"1905.11826","title":"Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion","created":"2019-05-28","cited_by_count":24},{"id":"1707.07113","title":"Adversarial Variational Optimization of Non-Differentiable Simulators","created":"2017-07-22","cited_by_count":22},{"id":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","cited_by_count":22},{"id":"1905.04598","title":"Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models","created":"2019-05-11","cited_by_count":18},{"id":"2012.05225","title":"MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias","created":"2020-12-09","cited_by_count":14},{"id":"2012.07138","title":"Learning Contextual Causality from Time-consecutive Images","created":"2020-12-13","cited_by_count":4}],"next_cursor":null}