{"list":"other","total":51,"rows":[{"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":"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":"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":"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"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":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2110.08733","title":"LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","created":"2021-10-17","cited_by_count":261},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"1904.10030","title":"Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks","created":"2019-04-22","cited_by_count":116},{"id":"2006.06606","title":"What makes instance discrimination good for transfer learning?","created":"2020-06-11","cited_by_count":111},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"2011.09766","title":"Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery","created":"2020-11-19","cited_by_count":73},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2104.12137","title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","created":"2021-04-25","cited_by_count":56},{"id":"1907.11357","title":"DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation","created":"2019-07-26","cited_by_count":45},{"id":"2005.02264","title":"LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery","created":"2020-05-05","cited_by_count":40},{"id":"1703.06452","title":"Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning","created":"2017-03-19","cited_by_count":37},{"id":"2007.03815","title":"Real-time Semantic Segmentation with Fast Attention","created":"2020-07-07","cited_by_count":36},{"id":"1803.06253","title":"Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models","created":"2018-03-16","cited_by_count":29},{"id":"2106.12413","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","created":"2021-06-23","cited_by_count":28},{"id":"1709.00179","title":"Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery","created":"2017-09-01","cited_by_count":20},{"id":"2111.08892","title":"SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining","created":"2021-11-17","cited_by_count":9},{"id":"2004.07124","title":"A Novel CNN-based Method for Accurate Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box","created":"2020-04-15","cited_by_count":8},{"id":"2211.15790","title":"Handling Image and Label Resolution Mismatch in Remote Sensing","created":"2022-11-28","cited_by_count":3},{"id":"2206.09731","title":"Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers","created":"2022-06-20","cited_by_count":1}],"next_cursor":null}