{"list":"other","total":59,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"2009.06962","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","created":"2020-09-15","cited_by_count":261},{"id":"1905.00397","title":"Fast AutoAugment","created":"2019-05-01","cited_by_count":243},{"id":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"2006.01791","title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization","created":"2020-06-02","cited_by_count":149},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131},{"id":"2102.03065","title":"Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity","created":"2021-02-05","cited_by_count":128},{"id":"1911.06987","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","created":"2019-11-16","cited_by_count":96},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"id":"2012.11101","title":"ResizeMix: Mixing Data with Preserved Object Information and True Labels","created":"2020-12-21","cited_by_count":69},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"2012.04846","title":"SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data","created":"2020-12-09","cited_by_count":56},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"1912.00145","title":"Point Cloud Instance Segmentation using Probabilistic Embeddings","created":"2019-11-30","cited_by_count":52},{"id":"2207.08409","title":"TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers","created":"2022-07-18","cited_by_count":48},{"id":"2202.12513","title":"TeachAugment: Data Augmentation Optimization Using Teacher Knowledge","created":"2022-02-25","cited_by_count":37},{"id":"2205.13943","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","created":"2022-05-27","cited_by_count":31},{"id":"2111.15454","title":"Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup","created":"2021-11-30","cited_by_count":22},{"id":"2209.04851","title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","created":"2022-09-11","cited_by_count":21},{"id":"2203.10761","title":"Harnessing Hard Mixed Samples with Decoupled Regularizer","created":"2022-03-21","cited_by_count":17},{"id":"2312.11954","title":"Adversarial AutoMixup","created":"2023-12-19","cited_by_count":16},{"id":"2112.08796","title":"Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing","created":"2021-12-16","cited_by_count":15},{"id":"2203.06844","title":"RecursiveMix: Mixed Learning with History","created":"2022-03-14","cited_by_count":15},{"id":"2304.12043","title":"MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer","created":"2023-04-24","cited_by_count":15},{"id":"2310.03013","title":"SemiReward: A General Reward Model for Semi-supervised Learning","created":"2023-10-04","cited_by_count":14},{"id":"2212.12977","title":"SMMix: Self-Motivated Image Mixing for Vision Transformers","created":"2022-12-26","cited_by_count":8},{"id":"2007.06096","title":"BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty","created":"2020-07-12","cited_by_count":7},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","cited_by_count":7},{"id":"2110.14553","title":"GenURL: A General Framework for Unsupervised Representation Learning","created":"2021-10-27","cited_by_count":6},{"id":"2211.15846","title":"LUMix: Improving Mixup by Better Modelling Label Uncertainty","created":"2022-11-29","cited_by_count":6},{"id":"2406.08128","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","created":"2024-06-12","cited_by_count":5}],"next_cursor":null}