{"list":"other","total":63,"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":"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"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":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"2009.12547","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","created":"2020-09-26","cited_by_count":229},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"1508.03422","title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","created":"2015-08-14","cited_by_count":167},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"1611.01353","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","created":"2016-11-04","cited_by_count":132},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"2103.01737","title":"Distilling Causal Effect of Data in Class-Incremental Learning","created":"2021-03-02","cited_by_count":117},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"2010.16412","title":"Empirical or Invariant Risk Minimization? A Sample Complexity Perspective","created":"2020-10-30","cited_by_count":62},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35}],"next_cursor":null}