{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"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":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"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":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2010.01028","title":"Hard Negative Mixing for Contrastive Learning","created":"2020-10-02","cited_by_count":402},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"2009.12547","title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","created":"2020-09-26","cited_by_count":229},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"1805.10180","title":"Pyramid Attention Network for Semantic Segmentation","created":"2018-05-25","cited_by_count":149},{"id":"2111.13998","title":"Targeted Supervised Contrastive Learning for Long-Tailed Recognition","created":"2021-11-27","cited_by_count":132},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"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":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84},{"id":"2007.12749","title":"Hard negative examples are hard, but useful","created":"2020-07-24","cited_by_count":82},{"id":"2003.05128","title":"Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks","created":"2020-03-11","cited_by_count":70},{"id":"2010.06682","title":"Are all negatives created equal in contrastive instance discrimination?","created":"2020-10-13","cited_by_count":50},{"id":"1803.10335","title":"Adaptive Affinity Fields for Semantic Segmentation","created":"2018-03-27","cited_by_count":48},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46},{"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":"2008.11702","title":"Delving into Inter-Image Invariance for Unsupervised Visual Representations","created":"2020-08-26","cited_by_count":37},{"id":"2207.08485","title":"Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation","created":"2022-07-18","cited_by_count":37},{"id":"2208.08352","title":"FCN-Transformer Feature Fusion for Polyp Segmentation","created":"2022-08-17","cited_by_count":37},{"id":"2104.03778","title":"Progressive Semantic Segmentation","created":"2021-04-08","cited_by_count":35},{"id":"2412.11890","title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","created":"2024-12-16","cited_by_count":31},{"id":"2302.02057","title":"Semantic Diffusion Network for Semantic Segmentation","created":"2023-02-04","cited_by_count":30},{"id":"2306.04842","title":"InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding","created":"2023-06-08","cited_by_count":22},{"id":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22},{"id":"2108.09702","title":"Self-Regulation for Semantic Segmentation","created":"2021-08-22","cited_by_count":18},{"id":"2205.07056","title":"Transformer Scale Gate for Semantic Segmentation","created":"2022-05-14","cited_by_count":17},{"id":"2401.11122","title":"Spatial Structure Constraints for Weakly Supervised Semantic Segmentation","created":"2024-01-20","cited_by_count":17},{"id":"2305.05154","title":"Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation","created":"2023-05-09","cited_by_count":16},{"id":"2401.07589","title":"Semantic Scene Segmentation for Robotics","created":"2024-01-15","cited_by_count":16},{"id":"2401.11414","title":"S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving","created":"2024-01-21","cited_by_count":15},{"id":"2404.10633","title":"Contextrast: Contextual Contrastive Learning for Semantic Segmentation","created":"2024-04-16","cited_by_count":12},{"id":"2203.13409","title":"Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation","created":"2022-03-25","cited_by_count":8},{"id":"2108.11128","title":"Semantic Scene Segmentation for Robotics Applications","created":"2021-08-25","cited_by_count":7},{"id":"2404.17793","title":"CLFT: Camera-LiDAR Fusion Transformer for Semantic Segmentation in Autonomous Driving","created":"2024-04-27","cited_by_count":7},{"id":"2501.01618","title":"Merging Context Clustering with Visual State Space Models for Medical Image Segmentation","created":"2025-01-03","cited_by_count":4}],"next_cursor":null}