{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"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":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"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":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"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":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2105.11120","title":"A Fourier-based Framework for Domain Generalization","created":"2021-05-24","cited_by_count":290},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"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":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215},{"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":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","cited_by_count":164},{"id":"2003.07325","title":"Domain Adaptive Ensemble Learning","created":"2020-03-16","cited_by_count":156},{"id":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","cited_by_count":138},{"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":"2008.12839","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","created":"2020-08-28","cited_by_count":128},{"id":"2202.03958","title":"Uncertainty Modeling for Out-of-Distribution Generalization","created":"2022-02-08","cited_by_count":125},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"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":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"1907.11216","title":"Domain Generalization via Multidomain Discriminant Analysis","created":"2019-07-25","cited_by_count":69},{"id":"1809.02256","title":"Multi-Source Domain Adaptation with Mixture of Experts","created":"2018-09-07","cited_by_count":62},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"2210.03885","title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","created":"2022-10-08","cited_by_count":50},{"id":"2204.03609","title":"Pin the Memory: Learning to Generalize Semantic Segmentation","created":"2022-04-07","cited_by_count":49},{"id":"2304.04494","title":"Improved Test-Time Adaptation for Domain Generalization","created":"2023-04-10","cited_by_count":47},{"id":"1611.05720","title":"Hard-Aware Deeply Cascaded Embedding","created":"2016-11-17","cited_by_count":44},{"id":"2203.13006","title":"Compound Domain Generalization via Meta-Knowledge Encoding","created":"2022-03-24","cited_by_count":40},{"id":"2103.01134","title":"Domain Generalization via Inference-time Label-Preserving Target Projections","created":"2021-03-01","cited_by_count":35},{"id":"2102.02811","title":"CrossNorm and SelfNorm for Generalization under Distribution Shifts","created":"2021-02-04","cited_by_count":33},{"id":"2112.02300","title":"Unsupervised Domain Generalization by Learning a Bridge Across Domains","created":"2021-12-04","cited_by_count":33},{"id":"2204.04384","title":"The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization","created":"2022-04-09","cited_by_count":21},{"id":"2210.07571","title":"Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization","created":"2022-10-14","cited_by_count":20},{"id":"2308.11158","title":"Domain Generalization via Rationale Invariance","created":"2023-08-22","cited_by_count":16},{"id":"1610.08904","title":"Local Similarity-Aware Deep Feature Embedding","created":"2016-10-27","cited_by_count":15},{"id":"2308.11911","title":"ACLS: Adaptive and Conditional Label Smoothing for Network Calibration","created":"2023-08-23","cited_by_count":15},{"id":"2403.08649","title":"A Causal Inspired Early-Branching Structure for Domain Generalization","created":"2024-03-13","cited_by_count":4},{"id":"1711.07758","title":"Understanding Deep Learning Generalization by Maximum Entropy","created":"2017-11-21","cited_by_count":3}],"next_cursor":null}