{"list":"other","total":58,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"1809.02499","title":"MixUp as Locally Linear Out-Of-Manifold Regularization","created":"2018-09-07","cited_by_count":158},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"1801.02929","title":"Data Augmentation by Pairing Samples for Images Classification","created":"2018-01-09","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":"1905.06023","title":"Distribution Calibration for Regression","created":"2019-05-15","cited_by_count":89},{"id":"1811.09030","title":"Data Augmentation using Random Image Cropping and Patching for Deep CNNs","created":"2018-11-22","cited_by_count":88},{"id":"1905.11659","title":"Evaluating and Calibrating Uncertainty Prediction in Regression Tasks","created":"2019-05-28","cited_by_count":87},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"1402.0929","title":"Input Warping for Bayesian Optimization of Non-stationary Functions","created":"2014-02-05","cited_by_count":67},{"id":"2105.02340","title":"DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data","created":"2021-05-05","cited_by_count":64},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60},{"id":"2210.05775","title":"C-Mixup: Improving Generalization in Regression","created":"2022-10-11","cited_by_count":57},{"id":"1711.10284","title":"Between-class Learning for Image Classification","created":"2017-11-28","cited_by_count":50},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49},{"id":"2010.09875","title":"Combining Ensembles and Data Augmentation can Harm your Calibration","created":"2020-10-19","cited_by_count":44},{"id":"1805.11272","title":"Improved Mixed-Example Data Augmentation","created":"2018-05-29","cited_by_count":42},{"id":"2102.12664","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","created":"2021-02-25","cited_by_count":39},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32},{"id":"2211.02291","title":"SelecMix: Debiased Learning by Contradicting-pair Sampling","created":"2022-11-04","cited_by_count":29},{"id":"2110.02180","title":"Noisy Feature Mixup","created":"2021-10-05","cited_by_count":27},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27},{"id":"2209.04851","title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","created":"2022-09-11","cited_by_count":21},{"id":"2108.00968","title":"Robust Semantic Segmentation with Superpixel-Mix","created":"2021-08-02","cited_by_count":19},{"id":"2110.07647","title":"Towards Understanding the Data Dependency of Mixup-style Training","created":"2021-10-14","cited_by_count":19},{"id":"2308.11990","title":"RankMixup: Ranking-Based Mixup Training for Network Calibration","created":"2023-08-23","cited_by_count":19},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17},{"id":"2106.02933","title":"k-Mixup Regularization for Deep Learning via Optimal Transport","created":"2021-06-05","cited_by_count":14},{"id":"2303.01475","title":"Over-training with Mixup May Hurt Generalization","created":"2023-03-02","cited_by_count":13},{"id":"1507.05880","title":"A study of the classification of low-dimensional data with supervised manifold learning","created":"2015-07-21","cited_by_count":9},{"id":"2306.02532","title":"R-Mixup: Riemannian Mixup for Biological Networks","created":"2023-06-05","cited_by_count":9},{"id":"2305.16817","title":"Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup","created":"2023-05-26","cited_by_count":8},{"id":"2108.09929","title":"SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness","created":"2021-08-23","cited_by_count":7},{"id":"2306.00267","title":"Provable Benefit of Mixup for Finding Optimal Decision Boundaries","created":"2023-06-01","cited_by_count":6}],"next_cursor":null}