{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1711.10925","title":"Deep Image Prior","created":"2017-11-29","cited_by_count":1098},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"1812.00564","title":"Split learning for health: Distributed deep learning without sharing raw patient data","created":"2018-12-03","cited_by_count":395},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1810.06060","title":"Distributed learning of deep neural network over multiple agents","created":"2018-10-14","cited_by_count":279},{"id":"1911.07135","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks","created":"2019-11-17","cited_by_count":246},{"id":"1711.09404","title":"Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients","created":"2017-11-26","cited_by_count":236},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"1710.04019","title":"An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists","created":"2017-10-11","cited_by_count":172},{"id":"1506.02158","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","created":"2015-06-06","cited_by_count":159},{"id":"1412.5068","title":"Towards Deep Neural Network Architectures Robust to Adversarial Examples","created":"2014-12-11","cited_by_count":146},{"id":"1511.06807","title":"Adding Gradient Noise Improves Learning for Very Deep Networks","created":"2015-11-21","cited_by_count":145},{"id":"1811.09310","title":"Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack","created":"2018-11-22","cited_by_count":125},{"id":"2001.02378","title":"MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius","created":"2020-01-08","cited_by_count":114},{"id":"1803.08680","title":"Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization","created":"2018-03-23","cited_by_count":88},{"id":"2012.08334","title":"Masksembles for Uncertainty Estimation","created":"2020-12-15","cited_by_count":88},{"id":"1904.03303","title":"Revealing Scenes by Inverting Structure from Motion Reconstructions","created":"2019-04-05","cited_by_count":66},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"1810.07481","title":"Provable Robustness of ReLU networks via Maximization of Linear Regions","created":"2018-10-17","cited_by_count":51},{"id":"1901.02731","title":"A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference","created":"2019-01-08","cited_by_count":51},{"id":"1904.05514","title":"Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach","created":"2019-04-11","cited_by_count":48},{"id":"1903.05572","title":"Privacy Preserving Image-Based Localization","created":"2019-03-13","cited_by_count":47},{"id":"1905.11468","title":"Scaleable input gradient regularization for adversarial robustness","created":"2019-05-27","cited_by_count":47},{"id":"1910.08640","title":"Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?","created":"2019-10-18","cited_by_count":43},{"id":"1802.04443","title":"On Characterizing the Capacity of Neural Networks using Algebraic Topology","created":"2018-02-13","cited_by_count":38},{"id":"2003.14348","title":"UniformAugment: A Search-free Probabilistic Data Augmentation Approach","created":"2020-03-31","cited_by_count":38},{"id":"2107.02425","title":"GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization","created":"2021-07-06","cited_by_count":34},{"id":"1902.01148","title":"Theoretical evidence for adversarial robustness through randomization","created":"2019-02-04","cited_by_count":33},{"id":"2003.12197","title":"HERS: Homomorphically Encrypted Representation Search","created":"2020-03-27","cited_by_count":26},{"id":"2104.05895","title":"IMAGINE: Image Synthesis by Image-Guided Model Inversion","created":"2021-04-13","cited_by_count":25},{"id":"2012.11025","title":"DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks","created":"2020-12-20","cited_by_count":23},{"id":"2006.11584","title":"Calibration of Model Uncertainty for Dropout Variational Inference","created":"2020-06-20","cited_by_count":18},{"id":"1807.11346","title":"Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators","created":"2018-07-30","cited_by_count":15},{"id":"1909.04126","title":"DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones","created":"2019-09-09","cited_by_count":15},{"id":"2101.01121","title":"Local Competition and Stochasticity for Adversarial Robustness in Deep Learning","created":"2021-01-04","cited_by_count":12},{"id":"1910.04257","title":"Membership Model Inversion Attacks for Deep Networks","created":"2019-10-09","cited_by_count":4},{"id":"1601.07213","title":"Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization","created":"2016-01-26","cited_by_count":1}],"next_cursor":null}