{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1907.08610","title":"Lookahead Optimizer: k steps forward, 1 step back","created":"2019-07-19","cited_by_count":336},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"1907.04275","title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","created":"2019-07-09","cited_by_count":161},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2007.13003","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","created":"2020-07-25","cited_by_count":142},{"id":"2004.14043","title":"Single-Side Domain Generalization for Face Anti-Spoofing","created":"2020-04-29","cited_by_count":139},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"1901.11448","title":"Feature-Critic Networks for Heterogeneous Domain Generalization","created":"2019-01-31","cited_by_count":130},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2009.12829","title":"Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization","created":"2020-09-27","cited_by_count":123},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98},{"id":"1510.04373","title":"Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization","created":"2015-10-15","cited_by_count":96},{"id":"2002.11841","title":"Towards Universal Representation Learning for Deep Face Recognition","created":"2020-02-26","cited_by_count":78},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57},{"id":"1904.12543","title":"Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization","created":"2019-04-29","cited_by_count":43},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27},{"id":"2402.18817","title":"Gradient Alignment for Cross-Domain Face Anti-Spoofing","created":"2024-02-29","cited_by_count":27},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15},{"id":"2210.06895","title":"GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization","created":"2022-10-13","cited_by_count":13},{"id":"2303.03300","title":"Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach","created":"2023-03-06","cited_by_count":12},{"id":"2405.18861","title":"Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts","created":"2024-05-29","cited_by_count":12},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10},{"id":"2403.07329","title":"Unknown Domain Inconsistency Minimization for Domain Generalization","created":"2024-03-12","cited_by_count":7},{"id":"2307.16704","title":"Lookbehind-SAM: k steps back, 1 step forward","created":"2023-07-31","cited_by_count":5},{"id":"2209.14742","title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","created":"2022-09-29","cited_by_count":2}],"next_cursor":null}