{"list":"other","total":58,"rows":[{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"1711.04340","title":"Data Augmentation Generative Adversarial Networks","created":"2017-11-12","cited_by_count":278},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"1912.01805","title":"Adversarial Domain Adaptation with Domain Mixup","created":"2019-12-04","cited_by_count":250},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"1905.00397","title":"Fast AutoAugment","created":"2019-05-01","cited_by_count":243},{"id":"2003.06054","title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","created":"2020-03-12","cited_by_count":231},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2010.04819","title":"How Does Mixup Help With Robustness and Generalization?","created":"2020-10-09","cited_by_count":193},{"id":"1801.10193","title":"DeepDTA: Deep Drug-Target Binding Affinity Prediction","created":"2018-01-30","cited_by_count":173},{"id":"2002.11684","title":"Provable Meta-Learning of Linear Representations","created":"2020-02-26","cited_by_count":161},{"id":"1809.02499","title":"MixUp as Locally Linear Out-Of-Manifold Regularization","created":"2018-09-07","cited_by_count":158},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"2006.01791","title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization","created":"2020-06-02","cited_by_count":149},{"id":"1906.11172","title":"Learning Data Augmentation Strategies for Object Detection","created":"2019-06-26","cited_by_count":139},{"id":"2102.03065","title":"Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity","created":"2021-02-05","cited_by_count":128},{"id":"1810.10863","title":"GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks","created":"2018-10-25","cited_by_count":107},{"id":"1912.03820","title":"Meta-Learning without Memorization","created":"2019-12-09","cited_by_count":92},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"1710.11622","title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","created":"2017-10-31","cited_by_count":65},{"id":"2007.05549","title":"Meta-Learning Requires Meta-Augmentation","created":"2020-07-10","cited_by_count":57},{"id":"2007.13040","title":"Improving Generalization in Meta-learning via Task Augmentation","created":"2020-07-26","cited_by_count":55},{"id":"2010.02322","title":"SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup","created":"2020-10-05","cited_by_count":52},{"id":"2207.08409","title":"TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers","created":"2022-07-18","cited_by_count":48},{"id":"2106.02695","title":"Meta-Learning with Fewer Tasks through Task Interpolation","created":"2021-06-04","cited_by_count":45},{"id":"2010.07092","title":"Data Augmentation for Meta-Learning","created":"2020-10-14","cited_by_count":38},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33},{"id":"2101.07732","title":"Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix","created":"2021-01-16","cited_by_count":27},{"id":"1810.06793","title":"Learning Two-layer Neural Networks with Symmetric Inputs","created":"2018-10-16","cited_by_count":22},{"id":"2203.04905","title":"What Matters For Meta-Learning Vision Regression Tasks?","created":"2022-03-09","cited_by_count":18},{"id":"2004.05859","title":"Regularizing Meta-Learning via Gradient Dropout","created":"2020-04-13","cited_by_count":15},{"id":"2112.08796","title":"Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing","created":"2021-12-16","cited_by_count":15},{"id":"2106.02933","title":"k-Mixup Regularization for Deep Learning via Optimal Transport","created":"2021-06-05","cited_by_count":14},{"id":"1907.07287","title":"Towards Understanding Generalization in Gradient-Based Meta-Learning","created":"2019-07-16","cited_by_count":12},{"id":"2203.09739","title":"Do Deep Networks Transfer Invariances Across Classes?","created":"2022-03-18","cited_by_count":12},{"id":"2201.04368","title":"Preventing Manifold Intrusion with Locality: Local Mixup","created":"2022-01-12","cited_by_count":11},{"id":"2106.09777","title":"On Invariance Penalties for Risk Minimization","created":"2021-06-17","cited_by_count":10}],"next_cursor":null}