{"list":"other","total":89,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"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":"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":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1810.08462","title":"Fully Convolutional Siamese Networks for Change Detection","created":"2018-10-19","cited_by_count":306},{"id":"2103.00208","title":"Remote Sensing Image Change Detection with Transformers","created":"2021-02-27","cited_by_count":306},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2201.01293","title":"A Transformer-Based Siamese Network for Change Detection","created":"2022-01-04","cited_by_count":244},{"id":"1902.06148","title":"BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding","created":"2019-02-16","cited_by_count":234},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"1908.05612","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","created":"2019-08-15","cited_by_count":194},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"id":"1703.01086","title":"Arbitrary-Oriented Scene Text Detection via Rotation Proposals","created":"2017-03-03","cited_by_count":176},{"id":"1910.13049","title":"Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation","created":"2019-10-29","cited_by_count":151},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"1809.00916","title":"OCNet: Object Context Network for Scene Parsing","created":"2018-09-04","cited_by_count":140},{"id":"1911.09358","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","created":"2019-11-21","cited_by_count":134},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2011.08612","title":"Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things","created":"2020-11-17","cited_by_count":111},{"id":"1803.05265","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","created":"2018-03-14","cited_by_count":88},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"2003.03608","title":"DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images","created":"2020-03-07","cited_by_count":75},{"id":"1911.08299","title":"Learning Modulated Loss for Rotated Object Detection","created":"2019-11-19","cited_by_count":73},{"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":"2005.01094","title":"Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities","created":"2020-05-03","cited_by_count":71},{"id":"2012.04150","title":"Dynamic Anchor Learning for Arbitrary-Oriented Object Detection","created":"2020-12-08","cited_by_count":70},{"id":"2108.07002","title":"Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery","created":"2021-08-16","cited_by_count":64},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"1706.09579","title":"R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection","created":"2017-06-29","cited_by_count":51},{"id":"2107.12636","title":"Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers","created":"2021-07-27","cited_by_count":49},{"id":"1807.02700","title":"Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery","created":"2018-07-07","cited_by_count":46},{"id":"2107.09600","title":"DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation","created":"2021-07-20","cited_by_count":45},{"id":"1903.00857","title":"CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery","created":"2019-03-03","cited_by_count":43},{"id":"2107.05276","title":"Geographical Knowledge-driven Representation Learning for Remote Sensing Images","created":"2021-07-12","cited_by_count":37},{"id":"2006.12119","title":"The color out of space: learning self-supervised representations for Earth Observation imagery","created":"2020-06-22","cited_by_count":34},{"id":"1904.05730","title":"A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes","created":"2019-04-11","cited_by_count":33},{"id":"2103.00188","title":"Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions","created":"2021-02-27","cited_by_count":23},{"id":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21},{"id":"2108.12611","title":"Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images","created":"2021-08-28","cited_by_count":20},{"id":"2004.04491","title":"Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification","created":"2020-04-09","cited_by_count":16},{"id":"1908.08156","title":"Multiple instance dense connected convolution neural network for aerial image scene classification","created":"2019-08-22","cited_by_count":15},{"id":"2111.12309","title":"RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?","created":"2021-11-24","cited_by_count":11},{"id":"2012.14569","title":"MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification","created":"2020-12-29","cited_by_count":10},{"id":"1911.08877","title":"Improving Semantic Segmentation of Aerial Images Using Patch-based Attention","created":"2019-11-20","cited_by_count":9},{"id":"2101.11189","title":"Arbitrary-Oriented Ship Detection through Center-Head Point Extraction","created":"2021-01-27","cited_by_count":9},{"id":"2104.00222","title":"Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classification","created":"2021-04-01","cited_by_count":8},{"id":"2201.01953","title":"Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling","created":"2022-01-06","cited_by_count":8},{"id":"2011.05702","title":"Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization","created":"2020-11-11","cited_by_count":4}],"next_cursor":null}