{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"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":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2004.02147","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","created":"2020-04-05","cited_by_count":294},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"1703.02719","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","created":"2017-03-08","cited_by_count":208},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167},{"id":"1907.05740","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","created":"2019-07-12","cited_by_count":166},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"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":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2002.10120","title":"Semantic Flow for Fast and Accurate Scene Parsing","created":"2020-02-24","cited_by_count":128},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"2210.05844","title":"SegViT: Semantic Segmentation with Plain Vision Transformers","created":"2022-10-12","cited_by_count":106},{"id":"2007.10035","title":"Improving Semantic Segmentation via Decoupled Body and Edge Supervision","created":"2020-07-20","cited_by_count":99},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76},{"id":"2112.12782","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","created":"2021-12-23","cited_by_count":55},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53},{"id":"2103.04133","title":"Learning Statistical Texture for Semantic Segmentation","created":"2021-03-06","cited_by_count":51},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2104.09805","title":"CTNet: Context-based Tandem Network for Semantic Segmentation","created":"2021-04-20","cited_by_count":43},{"id":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40},{"id":"2201.01615","title":"Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention","created":"2022-01-05","cited_by_count":30},{"id":"2203.12612","title":"StructToken : Rethinking Semantic Segmentation with Structural Prior","created":"2022-03-23","cited_by_count":30},{"id":"1807.07466","title":"Guided Upsampling Network for Real-Time Semantic Segmentation","created":"2018-07-19","cited_by_count":24},{"id":"2204.01969","title":"Region Rebalance for Long-Tailed Semantic Segmentation","created":"2022-04-05","cited_by_count":17},{"id":"2203.07160","title":"CAR: Class-aware Regularizations for Semantic Segmentation","created":"2022-03-14","cited_by_count":14},{"id":"2203.04187","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","created":"2022-03-08","cited_by_count":11}],"next_cursor":null}