{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"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":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"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":"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":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1812.03411","title":"Feature Denoising for Improving Adversarial Robustness","created":"2018-12-09","cited_by_count":314},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"1911.09665","title":"Adversarial Examples Improve Image Recognition","created":"2019-11-21","cited_by_count":286},{"id":"2010.03593","title":"Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples","created":"2020-10-07","cited_by_count":278},{"id":"1808.08750","title":"Generalisation in humans and deep neural networks","created":"2018-08-27","cited_by_count":237},{"id":"1803.06373","title":"Adversarial Logit Pairing","created":"2018-03-16","cited_by_count":224},{"id":"2007.02617","title":"Understanding and Improving Fast Adversarial Training","created":"2020-07-06","cited_by_count":214},{"id":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"1811.09716","title":"Robustness via curvature regularization, and vice versa","created":"2018-11-23","cited_by_count":175},{"id":"1812.00740","title":"Disentangling Adversarial Robustness and Generalization","created":"2018-12-03","cited_by_count":172},{"id":"1901.10513","title":"Adversarial Examples Are a Natural Consequence of Test Error in Noise","created":"2019-01-29","cited_by_count":114},{"id":"1705.02498","title":"A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions","created":"2017-05-06","cited_by_count":108},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97},{"id":"1811.11304","title":"Universal Adversarial Training","created":"2018-11-27","cited_by_count":87},{"id":"1802.09653","title":"On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples","created":"2018-02-27","cited_by_count":58},{"id":"1910.04284","title":"Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin","created":"2019-10-09","cited_by_count":56},{"id":"2007.08450","title":"Learning perturbation sets for robust machine learning","created":"2020-07-16","cited_by_count":48},{"id":"1807.10272","title":"Evaluating and Understanding the Robustness of Adversarial Logit Pairing","created":"2018-07-26","cited_by_count":34},{"id":"1511.05432","title":"Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization","created":"2015-11-17","cited_by_count":32},{"id":"2002.06349","title":"Hold me tight! Influence of discriminative features on deep network boundaries","created":"2020-02-15","cited_by_count":31},{"id":"1810.12042","title":"Logit Pairing Methods Can Fool Gradient-Based Attacks","created":"2018-10-29","cited_by_count":27},{"id":"2005.10247","title":"Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data","created":"2020-05-20","cited_by_count":27},{"id":"1905.01034","title":"Transfer of Adversarial Robustness Between Perturbation Types","created":"2019-05-03","cited_by_count":25},{"id":"1807.04200","title":"With Friends Like These, Who Needs Adversaries?","created":"2018-07-11","cited_by_count":19},{"id":"1906.07153","title":"Adversarial attacks on Copyright Detection Systems","created":"2019-06-17","cited_by_count":11},{"id":"2011.05157","title":"Bridging the Performance Gap between FGSM and PGD Adversarial Training","created":"2020-11-07","cited_by_count":9},{"id":"1906.00735","title":"Achieving Generalizable Robustness of Deep Neural Networks by Stability Training","created":"2019-06-03","cited_by_count":7}],"next_cursor":null}