{"list":"other","total":87,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"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":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"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":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"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":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"1908.07086","title":"Human uncertainty makes classification more robust","created":"2019-08-19","cited_by_count":235},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186},{"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":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2003.12815","title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","created":"2020-03-28","cited_by_count":134},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"id":"1901.11448","title":"Feature-Critic Networks for Heterogeneous Domain Generalization","created":"2019-01-31","cited_by_count":130},{"id":"2101.01134","title":"Does Invariant Risk Minimization Capture Invariance?","created":"2021-01-04","cited_by_count":116},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104},{"id":"2007.07645","title":"Learning to Learn with Variational Information Bottleneck for Domain Generalization","created":"2020-07-15","cited_by_count":102},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"2106.06333","title":"Invariant Information Bottleneck for Domain Generalization","created":"2021-06-11","cited_by_count":86},{"id":"2110.09410","title":"Exploiting Domain-Specific Features to Enhance Domain Generalization","created":"2021-10-18","cited_by_count":86},{"id":"2106.07617","title":"Delving Deep into the Generalization of Vision Transformers under Distribution Shifts","created":"2021-06-14","cited_by_count":85},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78},{"id":"1711.01244","title":"Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory","created":"2017-11-03","cited_by_count":76},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57},{"id":"2208.08914","title":"Prompt Vision Transformer for Domain Generalization","created":"2022-08-18","cited_by_count":52},{"id":"2106.02266","title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","created":"2021-06-04","cited_by_count":50},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50},{"id":"2012.09382","title":"DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation","created":"2020-12-17","cited_by_count":48},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36},{"id":"1910.11645","title":"Reducing Domain Gap by Reducing Style Bias","created":"2019-10-25","cited_by_count":35},{"id":"1705.10874","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","created":"2017-05-30","cited_by_count":30},{"id":"2203.04600","title":"Domain Generalization using Pretrained Models without Fine-tuning","created":"2022-03-09","cited_by_count":29},{"id":"2109.02038","title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","created":"2021-09-05","cited_by_count":28},{"id":"2009.09496","title":"Learning Soft Labels via Meta Learning","created":"2020-09-20","cited_by_count":27},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27},{"id":"1703.03091","title":"Deep Learning applied to NLP","created":"2017-03-09","cited_by_count":11},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11},{"id":"1601.04114","title":"Training Recurrent Neural Networks by Diffusion","created":"2016-01-16","cited_by_count":9},{"id":"2305.19953","title":"Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing","created":"2023-05-31","cited_by_count":9}],"next_cursor":null}