{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"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":"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":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"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":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"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":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"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":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189},{"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":"1911.07661","title":"Domain Generalization Using a Mixture of Multiple Latent Domains","created":"2019-11-18","cited_by_count":170},{"id":"2003.07325","title":"Domain Adaptive Ensemble Learning","created":"2020-03-16","cited_by_count":156},{"id":"2203.14237","title":"Causality Inspired Representation Learning for Domain Generalization","created":"2022-03-27","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":"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":"2108.04443","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","created":"2021-08-10","cited_by_count":121},{"id":"1905.10427","title":"DIVA: Domain Invariant Variational Autoencoders","created":"2019-05-24","cited_by_count":115},{"id":"1904.12347","title":"Domain Agnostic Learning with Disentangled Representations","created":"2019-04-28","cited_by_count":108},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98},{"id":"2004.01959","title":"Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning","created":"2020-04-04","cited_by_count":93},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91},{"id":"2010.06208","title":"DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets","created":"2020-10-13","cited_by_count":70},{"id":"2108.01621","title":"Domain Generalization via Gradient Surgery","created":"2021-08-03","cited_by_count":60},{"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":"2304.00424","title":"Progressive Random Convolutions for Single Domain Generalization","created":"2023-04-02","cited_by_count":34},{"id":"2010.07591","title":"Respecting Domain Relations: Hypothesis Invariance for Domain Generalization","created":"2020-10-15","cited_by_count":30},{"id":"2402.18817","title":"Gradient Alignment for Cross-Domain Face Anti-Spoofing","created":"2024-02-29","cited_by_count":27},{"id":"2101.09060","title":"Rethinking Domain Generalization Baselines","created":"2021-01-22","cited_by_count":26},{"id":"1511.04210","title":"On the Quality of the Initial Basin in Overspecified Neural Networks","created":"2015-11-13","cited_by_count":20},{"id":"2303.11338","title":"Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks","created":"2023-03-20","cited_by_count":14},{"id":"2011.06207","title":"Domain Generalization in Biosignal Classification","created":"2020-11-12","cited_by_count":8},{"id":"2304.04858","title":"Simulated Annealing in Early Layers Leads to Better Generalization","created":"2023-04-10","cited_by_count":6},{"id":"2107.07558","title":"SA-GD: Improved Gradient Descent Learning Strategy with Simulated Annealing","created":"2021-07-15","cited_by_count":4},{"id":"2308.14418","title":"Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization","created":"2023-08-28","cited_by_count":4},{"id":"2203.02201","title":"Neural Simulated Annealing","created":"2022-03-04","cited_by_count":2}],"next_cursor":null}