{"list":"other","total":77,"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"1901.00976","title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","created":"2019-01-04","cited_by_count":407},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"1605.09522","title":"Kernel Mean Embedding of Distributions: A Review and Beyond","created":"2016-05-31","cited_by_count":364},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1612.05424","title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks","created":"2016-12-16","cited_by_count":308},{"id":"1809.09478","title":"Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation","created":"2018-09-25","cited_by_count":295},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2006.10963","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","created":"2020-06-19","cited_by_count":236},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"1809.02176","title":"Multi-Adversarial Domain Adaptation","created":"2018-09-04","cited_by_count":196},{"id":"2303.13899","title":"Robust Test-Time Adaptation in Dynamic Scenarios","created":"2023-03-24","cited_by_count":189},{"id":"2012.07297","title":"Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer","created":"2020-12-14","cited_by_count":173},{"id":"2204.13132","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","created":"2022-04-27","cited_by_count":164},{"id":"1702.08400","title":"Asymmetric Tri-training for Unsupervised Domain Adaptation","created":"2017-02-27","cited_by_count":152},{"id":"1906.02337","title":"MNIST-C: A Robustness Benchmark for Computer Vision","created":"2019-06-05","cited_by_count":138},{"id":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131},{"id":"2011.09230","title":"FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation","created":"2020-11-18","cited_by_count":124},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"2211.13081","title":"Robust Mean Teacher for Continual and Gradual Test-Time Adaptation","created":"2022-11-23","cited_by_count":104},{"id":"1910.03723","title":"Knowledge Distillation from Internal Representations","created":"2019-10-08","cited_by_count":87},{"id":"1805.07925","title":"Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks","created":"2018-05-21","cited_by_count":78},{"id":"2106.05528","title":"Cross-domain Contrastive Learning for Unsupervised Domain Adaptation","created":"2021-06-10","cited_by_count":76},{"id":"1911.12036","title":"Discriminative Adversarial Domain Adaptation","created":"2019-11-27","cited_by_count":74},{"id":"1904.07848","title":"Active Adversarial Domain Adaptation","created":"2019-04-16","cited_by_count":73},{"id":"2103.02325","title":"On the effectiveness of adversarial training against common corruptions","created":"2021-03-03","cited_by_count":71},{"id":"2103.16201","title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","created":"2021-03-30","cited_by_count":65},{"id":"2107.05446","title":"Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration","created":"2021-07-12","cited_by_count":50},{"id":"2203.01761","title":"Doubly Robust Calibration of Prediction Sets under Covariate Shift","created":"2022-03-03","cited_by_count":40},{"id":"2210.11389","title":"TTTFlow: Unsupervised Test-Time Training with Normalizing Flow","created":"2022-10-20","cited_by_count":33},{"id":"2206.14973","title":"Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology","created":"2022-06-30","cited_by_count":26},{"id":"2311.14402","title":"TEA: Test-time Energy Adaptation","created":"2023-11-24","cited_by_count":25},{"id":"2001.02950","title":"Generative Pseudo-label Refinement for Unsupervised Domain Adaptation","created":"2020-01-09","cited_by_count":24},{"id":"2208.00461","title":"Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks","created":"2022-07-31","cited_by_count":24},{"id":"2006.01683","title":"Channel Distillation: Channel-Wise Attention for Knowledge Distillation","created":"2020-06-02","cited_by_count":21},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16},{"id":"2311.04991","title":"Effective Restoration of Source Knowledge in Continual Test Time Adaptation","created":"2023-11-08","cited_by_count":15},{"id":"2101.06459","title":"Robustness to Augmentations as a Generalization metric","created":"2021-01-16","cited_by_count":13},{"id":"2108.12867","title":"Partial Domain Adaptation without Domain Alignment","created":"2021-08-29","cited_by_count":11},{"id":"2110.10536","title":"Improving Model Generalization by Agreement of Learned Representations from Data Augmentation","created":"2021-10-20","cited_by_count":5},{"id":"1909.04202","title":"Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults","created":"2019-09-10","cited_by_count":3},{"id":"2208.11176","title":"A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels","created":"2022-08-23","cited_by_count":3},{"id":"2410.11271","title":"Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation","created":"2024-10-15","cited_by_count":1}],"next_cursor":null}