{"list":"other","total":87,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"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":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"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":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2111.14791","title":"Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis","created":"2021-11-29","cited_by_count":422},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"1904.00625","title":"Med3D: Transfer Learning for 3D Medical Image Analysis","created":"2019-04-01","cited_by_count":288},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"2102.08005","title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","created":"2021-02-16","cited_by_count":258},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245},{"id":"2103.03024","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","created":"2021-03-04","cited_by_count":227},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"1908.06912","title":"Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis","created":"2019-08-19","cited_by_count":159},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2003.00827","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","created":"2020-02-14","cited_by_count":153},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"2209.07098","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","created":"2022-09-15","cited_by_count":104},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"2106.07617","title":"Delving Deep into the Generalization of Vision Transformers under Distribution Shifts","created":"2021-06-14","cited_by_count":85},{"id":"2103.08700","title":"Deep Learning for Chest X-ray Analysis: A Survey","created":"2021-03-15","cited_by_count":84},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73},{"id":"2102.10680","title":"Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning","created":"2021-02-21","cited_by_count":68},{"id":"2108.09038","title":"Is it Time to Replace CNNs with Transformers for Medical Images?","created":"2021-08-20","cited_by_count":60},{"id":"1803.02315","title":"Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification","created":"2018-03-06","cited_by_count":57},{"id":"2005.12734","title":"Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labels","created":"2020-05-25","cited_by_count":56},{"id":"1711.06373","title":"Thoracic Disease Identification and Localization with Limited Supervision","created":"2017-11-17","cited_by_count":55},{"id":"2204.10437","title":"DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis","created":"2022-04-21","cited_by_count":48},{"id":"1711.08998","title":"Visual Feature Attribution using Wasserstein GANs","created":"2017-11-24","cited_by_count":47},{"id":"2007.08826","title":"Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation","created":"2020-07-17","cited_by_count":40},{"id":"1908.06965","title":"Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization","created":"2019-08-16","cited_by_count":38},{"id":"1904.06197","title":"Simulation of hyperelastic materials in real-time using Deep Learning","created":"2019-04-10","cited_by_count":35},{"id":"2007.06959","title":"Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration","created":"2020-07-14","cited_by_count":35},{"id":"2111.12918","title":"ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification","created":"2021-11-25","cited_by_count":35},{"id":"1803.04565","title":"Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks","created":"2018-03-12","cited_by_count":33},{"id":"1807.07532","title":"Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs","created":"2018-07-19","cited_by_count":32},{"id":"2108.05930","title":"A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis","created":"2021-08-12","cited_by_count":31},{"id":"1803.07703","title":"Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions","created":"2018-03-21","cited_by_count":22},{"id":"2007.10859","title":"Multi-label Thoracic Disease Image Classification with Cross-Attention Networks","created":"2020-07-21","cited_by_count":22},{"id":"2109.12265","title":"Label-Assemble: Leveraging Multiple Datasets with Partial Labels","created":"2021-09-25","cited_by_count":20},{"id":"2204.07344","title":"CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging","created":"2022-04-15","cited_by_count":18},{"id":"2005.10550","title":"Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification","created":"2020-05-21","cited_by_count":15},{"id":"2203.11725","title":"Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder","created":"2022-03-22","cited_by_count":15},{"id":"2109.06232","title":"The Emergence of the Shape Bias Results from Communicative Efficiency","created":"2021-09-13","cited_by_count":13},{"id":"2103.07055","title":"Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus","created":"2021-03-12","cited_by_count":12},{"id":"2206.04246","title":"SwinCheX: Multi-label classification on chest X-ray images with transformers","created":"2022-06-09","cited_by_count":12},{"id":"1807.00958","title":"Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays","created":"2018-07-03","cited_by_count":10},{"id":"1611.08664","title":"Semi-supervised Learning using Denoising Autoencoders for Brain Lesion Detection and Segmentation","created":"2016-11-26","cited_by_count":6},{"id":"2210.08054","title":"Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment","created":"2022-10-14","cited_by_count":6}],"next_cursor":null}