{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"1706.08576","title":"Invariant Causal Prediction for Nonlinear Models","created":"2017-06-26","cited_by_count":140},{"id":"2007.02561","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","created":"2020-07-06","cited_by_count":133},{"id":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2006.07886","title":"On Disentangled Representations Learned From Correlated Data","created":"2020-06-14","cited_by_count":94},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85},{"id":"1804.00104","title":"Learning Disentangled Joint Continuous and Discrete Representations","created":"2018-03-31","cited_by_count":83},{"id":"1804.02391","title":"Learn To Pay Attention","created":"2018-04-06","cited_by_count":83},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80},{"id":"2012.09276","title":"Measuring Disentanglement: A Review of Metrics","created":"2020-12-16","cited_by_count":70},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2306.11074","title":"Simple and Fast Group Robustness by Automatic Feature Reweighting","created":"2023-06-19","cited_by_count":68},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66},{"id":"1905.01258","title":"Disentangling Factors of Variation Using Few Labels","created":"2019-05-03","cited_by_count":57},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41},{"id":"2103.13447","title":"DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation","created":"2021-03-24","cited_by_count":37},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36},{"id":"2108.03553","title":"Self-Adversarial Disentangling for Specific Domain Adaptation","created":"2021-08-08","cited_by_count":29},{"id":"1902.01568","title":"Relevance Factor VAE: Learning and Identifying Disentangled Factors","created":"2019-02-05","cited_by_count":20},{"id":"2305.02995","title":"Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations","created":"2023-05-04","cited_by_count":7},{"id":"1607.03300","title":"From Dependence to Causation","created":"2016-07-12","cited_by_count":6},{"id":"2306.11120","title":"Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts","created":"2023-06-19","cited_by_count":5}],"next_cursor":null}