{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"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":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"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":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"2201.05718","title":"Parameter-free Online Test-time Adaptation","created":"2022-01-15","cited_by_count":189},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116},{"id":"2207.09640","title":"Test-Time Adaptation via Conjugate Pseudo-labels","created":"2022-07-20","cited_by_count":98},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86},{"id":"1711.10288","title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","created":"2017-11-28","cited_by_count":71},{"id":"2306.03536","title":"On Pitfalls of Test-Time Adaptation","created":"2023-06-06","cited_by_count":64},{"id":"2204.12511","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","created":"2022-04-26","cited_by_count":63},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53},{"id":"2108.10860","title":"Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density","created":"2021-08-24","cited_by_count":44},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44},{"id":"2104.12928","title":"If your data distribution shifts, use self-learning","created":"2021-04-27","cited_by_count":36},{"id":"2012.15483","title":"Why do classifier accuracies show linear trends under distribution shift?","created":"2020-12-31","cited_by_count":21},{"id":"2208.07360","title":"Three New Validators and a Large-Scale Benchmark Ranking for Unsupervised Domain Adaptation","created":"2022-08-15","cited_by_count":13},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12},{"id":"2210.10019","title":"Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation","created":"2022-10-18","cited_by_count":9},{"id":"2210.11589","title":"Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization","created":"2022-10-20","cited_by_count":2}],"next_cursor":null}