{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1804.11285","title":"Adversarially Robust Generalization Requires More Data","created":"2018-04-30","cited_by_count":318},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"1911.09665","title":"Adversarial Examples Improve Image Recognition","created":"2019-11-21","cited_by_count":286},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234},{"id":"1803.10837","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","created":"2018-03-28","cited_by_count":213},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208},{"id":"2002.10716","title":"Understanding and Mitigating the Tradeoff Between Robustness and Accuracy","created":"2020-02-25","cited_by_count":149},{"id":"1907.02610","title":"Adversarial Robustness through Local Linearization","created":"2019-07-04","cited_by_count":146},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133},{"id":"1905.09747","title":"Adversarially Robust Distillation","created":"2019-05-23","cited_by_count":125},{"id":"1912.11188","title":"Adversarial AutoAugment","created":"2019-12-24","cited_by_count":111},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104},{"id":"2204.08610","title":"Image Data Augmentation for Deep Learning: A Survey","created":"2022-04-19","cited_by_count":96},{"id":"1911.10891","title":"ColorFool: Semantic Adversarial Colorization","created":"2019-11-25","cited_by_count":89},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79},{"id":"2010.05981","title":"Shape-Texture Debiased Neural Network Training","created":"2020-10-12","cited_by_count":76},{"id":"2012.08674","title":"Wasserstein Contrastive Representation Distillation","created":"2020-12-15","cited_by_count":64},{"id":"2003.08436","title":"Collaborative Distillation for Ultra-Resolution Universal Style Transfer","created":"2020-03-18","cited_by_count":52},{"id":"2103.04623","title":"Consistency Regularization for Adversarial Robustness","created":"2021-03-08","cited_by_count":42},{"id":"2309.12530","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","created":"2023-09-21","cited_by_count":40},{"id":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39},{"id":"2012.02909","title":"What Makes a \"Good\" Data Augmentation in Knowledge Distillation -- A Statistical Perspective","created":"2020-12-05","cited_by_count":35},{"id":"2111.10493","title":"Discrete Representations Strengthen Vision Transformer Robustness","created":"2021-11-20","cited_by_count":35},{"id":"1811.05232","title":"Theoretical Analysis of Adversarial Learning: A Minimax Approach","created":"2018-11-13","cited_by_count":31},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30},{"id":"1912.03192","title":"Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations","created":"2019-12-06","cited_by_count":28},{"id":"2104.01086","title":"Defending Against Image Corruptions Through Adversarial Augmentations","created":"2021-04-02","cited_by_count":28},{"id":"2002.09024","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","created":"2020-02-20","cited_by_count":27},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23},{"id":"2210.04886","title":"Revisiting adapters with adversarial training","created":"2022-10-10","cited_by_count":18},{"id":"2303.13846","title":"Feature Separation and Recalibration for Adversarial Robustness","created":"2023-03-24","cited_by_count":16},{"id":"2206.01909","title":"Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation","created":"2022-06-04","cited_by_count":11},{"id":"2204.09838","title":"Fast AdvProp","created":"2022-04-21","cited_by_count":6},{"id":"2308.10632","title":"Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models","created":"2023-08-21","cited_by_count":6}],"next_cursor":null}