{"list":"other","total":112,"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":"2103.00020","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":"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"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":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"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":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"1901.03429","title":"On the Turing Completeness of Modern Neural Network Architectures","created":"2019-01-10","cited_by_count":129},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"2103.15670","title":"On the Adversarial Robustness of Vision Transformers","created":"2021-03-29","cited_by_count":106},{"id":"2212.04145","title":"Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation","created":"2022-12-08","cited_by_count":98},{"id":"2210.04831","title":"Visual Prompt Tuning for Test-time Domain Adaptation","created":"2022-10-10","cited_by_count":97},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89},{"id":"2106.07617","title":"Delving Deep into the Generalization of Vision Transformers under Distribution Shifts","created":"2021-06-14","cited_by_count":85},{"id":"2108.09038","title":"Is it Time to Replace CNNs with Transformers for Medical Images?","created":"2021-08-20","cited_by_count":60},{"id":"2303.13434","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","created":"2023-03-23","cited_by_count":54},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46},{"id":"1808.07507","title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","created":"2018-08-22","cited_by_count":40},{"id":"2106.06112","title":"Spectral Unsupervised Domain Adaptation for Visual Recognition","created":"2021-06-11","cited_by_count":40},{"id":"1409.5403","title":"Deformable Part Models are Convolutional Neural Networks","created":"2014-09-18","cited_by_count":35},{"id":"2207.12392","title":"Self-Distilled Vision Transformer for Domain Generalization","created":"2022-07-25","cited_by_count":35},{"id":"2211.15393","title":"Video Test-Time Adaptation for Action Recognition","created":"2022-11-24","cited_by_count":35},{"id":"1811.03879","title":"Cross and Learn: Cross-Modal Self-Supervision","created":"2018-11-09","cited_by_count":34},{"id":"2305.13031","title":"HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation","created":"2023-05-22","cited_by_count":32},{"id":"2105.14138","title":"Transformer-Based Source-Free Domain Adaptation","created":"2021-05-28","cited_by_count":30},{"id":"2211.03876","title":"CoNMix for Source-free Single and Multi-target Domain Adaptation","created":"2022-11-07","cited_by_count":23},{"id":"2209.06993","title":"Learning from Future: A Novel Self-Training Framework for Semantic Segmentation","created":"2022-09-15","cited_by_count":21},{"id":"2107.11011","title":"VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data","created":"2021-07-23","cited_by_count":19},{"id":"2304.11862","title":"Universal Domain Adaptation via Compressive Attention Matching","created":"2023-04-24","cited_by_count":15},{"id":"2201.05887","title":"Domain Adaptation via Bidirectional Cross-Attention Transformer","created":"2022-01-15","cited_by_count":13},{"id":"2208.14227","title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","created":"2022-08-27","cited_by_count":13},{"id":"2209.01121","title":"Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization","created":"2022-09-02","cited_by_count":12},{"id":"2312.07460","title":"Empirical Validation of Conformal Prediction for Trustworthy Skin Lesions Classification","created":"2023-12-12","cited_by_count":11},{"id":"2201.11620","title":"Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study","created":"2022-01-27","cited_by_count":10},{"id":"2207.12842","title":"Unsupervised Domain Adaptation for Video Transformers in Action Recognition","created":"2022-07-26","cited_by_count":10},{"id":"2303.15698","title":"TFS-ViT: Token-Level Feature Stylization for Domain Generalization","created":"2023-03-28","cited_by_count":10},{"id":"2304.12122","title":"Augmentation-based Domain Generalization for Semantic Segmentation","created":"2023-04-24","cited_by_count":10},{"id":"2204.11891","title":"ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer","created":"2022-04-25","cited_by_count":9},{"id":"2304.01508","title":"EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition","created":"2023-04-04","cited_by_count":9},{"id":"2307.02100","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","created":"2023-07-05","cited_by_count":9},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8},{"id":"2305.14269","title":"Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers","created":"2023-05-23","cited_by_count":8},{"id":"2111.12941","title":"Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation","created":"2021-11-25","cited_by_count":7},{"id":"2208.01195","title":"Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation","created":"2022-08-02","cited_by_count":7}],"next_cursor":"100"}