{"list":"other","total":68,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"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":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1907.02044","title":"Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack","created":"2019-07-03","cited_by_count":334},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"2204.10377","title":"Contrastive Test-Time Adaptation","created":"2022-04-21","cited_by_count":261},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"1704.06369","title":"NormFace: L2 Hypersphere Embedding for Face Verification","created":"2017-04-21","cited_by_count":237},{"id":"1905.05702","title":"Sparse Sequence-to-Sequence Models","created":"2019-05-14","cited_by_count":170},{"id":"1907.04275","title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","created":"2019-07-09","cited_by_count":161},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"1901.02324","title":"Learning with Fenchel-Young Losses","created":"2019-01-08","cited_by_count":119},{"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":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"id":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97},{"id":"1703.09507","title":"L2-constrained Softmax Loss for Discriminative Face Verification","created":"2017-03-28","cited_by_count":96},{"id":"2202.12040","title":"Self-Training: A Survey","created":"2022-02-24","cited_by_count":86},{"id":"2106.01899","title":"Adversarially Adaptive Normalization for Single Domain Generalization","created":"2021-06-01","cited_by_count":85},{"id":"1905.00292","title":"AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations","created":"2019-05-01","cited_by_count":83},{"id":"2106.05961","title":"What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?","created":"2021-06-10","cited_by_count":63},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60},{"id":"2007.03511","title":"Estimating Generalization under Distribution Shifts via Domain-Invariant Representations","created":"2020-07-06","cited_by_count":56},{"id":"2106.15728","title":"Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles","created":"2021-06-29","cited_by_count":54},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50},{"id":"1805.05532","title":"Knowledge Distillation with Adversarial Samples Supporting Decision Boundary","created":"2018-05-15","cited_by_count":49},{"id":"2104.12928","title":"If your data distribution shifts, use self-learning","created":"2021-04-27","cited_by_count":36},{"id":"1912.11460","title":"Characterizing the Decision Boundary of Deep Neural Networks","created":"2019-12-24","cited_by_count":32},{"id":"1511.05042","title":"An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family","created":"2015-11-16","cited_by_count":27},{"id":"1705.07086","title":"Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach","created":"2017-05-19","cited_by_count":27},{"id":"1805.09717","title":"Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms","created":"2018-05-24","cited_by_count":27},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22},{"id":"1708.03769","title":"Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation","created":"2017-08-12","cited_by_count":21},{"id":"2002.01810","title":"Understanding the Decision Boundary of Deep Neural Networks: An Empirical Study","created":"2020-02-05","cited_by_count":20},{"id":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20},{"id":"2104.00941","title":"Multi-Class Data Description for Out-of-distribution Detection","created":"2021-04-02","cited_by_count":19},{"id":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17},{"id":"1609.04495","title":"Tsallis Regularized Optimal Transport and Ecological Inference","created":"2016-09-15","cited_by_count":15},{"id":"2303.15488","title":"On the Importance of Feature Separability in Predicting Out-Of-Distribution Error","created":"2023-03-27","cited_by_count":15},{"id":"1808.05385","title":"On the Decision Boundary of Deep Neural Networks","created":"2018-08-16","cited_by_count":11},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11},{"id":"2101.09849","title":"Deep Learning Generalization and the Convex Hull of Training Sets","created":"2021-01-25","cited_by_count":10},{"id":"1905.06005","title":"Geometric Losses for Distributional Learning","created":"2019-05-15","cited_by_count":7},{"id":"2310.14814","title":"Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias","created":"2023-10-23","cited_by_count":7},{"id":"2310.13434","title":"Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption","created":"2023-10-20","cited_by_count":6}],"next_cursor":null}