{"list":"other","total":51,"rows":[{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"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":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"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":"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":"2006.13009","title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","created":"2020-06-21","cited_by_count":214},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"2002.02923","title":"Geometric Dataset Distances via Optimal Transport","created":"2020-02-07","cited_by_count":158},{"id":"2104.03620","title":"Open Domain Generalization with Domain-Augmented Meta-Learning","created":"2021-04-08","cited_by_count":115},{"id":"2009.05448","title":"Heterogeneous Domain Generalization via Domain Mixup","created":"2020-09-11","cited_by_count":103},{"id":"2110.09410","title":"Exploiting Domain-Specific Features to Enhance Domain Generalization","created":"2021-10-18","cited_by_count":86},{"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":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83},{"id":"2105.09156","title":"Generalizable Person Re-identification with Relevance-aware Mixture of Experts","created":"2021-05-19","cited_by_count":77},{"id":"2301.13018","title":"DELTA: degradation-free fully test-time adaptation","created":"2023-01-30","cited_by_count":72},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2103.16201","title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","created":"2021-03-30","cited_by_count":65},{"id":"2210.05775","title":"C-Mixup: Improving Generalization in Regression","created":"2022-10-11","cited_by_count":57},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2201.09637","title":"DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations","created":"2022-01-24","cited_by_count":54},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"1903.07062","title":"AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs","created":"2019-03-17","cited_by_count":32},{"id":"2203.04600","title":"Domain Generalization using Pretrained Models without Fine-tuning","created":"2022-03-09","cited_by_count":29},{"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":"2202.03628","title":"Graph-Relational Domain Adaptation","created":"2022-02-08","cited_by_count":19},{"id":"2210.06807","title":"Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors","created":"2022-10-13","cited_by_count":17},{"id":"2207.11221","title":"Domain Generalization for Activity Recognition via Adaptive Feature Fusion","created":"2022-07-21","cited_by_count":16},{"id":"2203.04695","title":"Structured Multi-task Learning for Molecular Property Prediction","created":"2022-02-22","cited_by_count":12},{"id":"2106.09777","title":"On Invariance Penalties for Risk Minimization","created":"2021-06-17","cited_by_count":10},{"id":"2302.02350","title":"Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalization","created":"2023-02-05","cited_by_count":8}],"next_cursor":null}