{"list":"other","total":55,"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":"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"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":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"2304.10517","title":"Segment Anything Model for Medical Image Analysis: an Experimental Study","created":"2023-04-20","cited_by_count":291},{"id":"1904.00625","title":"Med3D: Transfer Learning for 3D Medical Image Analysis","created":"2019-04-01","cited_by_count":288},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"1603.07485","title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","created":"2016-03-24","cited_by_count":227},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"1611.04849","title":"Deeply supervised salient object detection with short connections","created":"2016-11-15","cited_by_count":196},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2102.06191","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","created":"2021-02-11","cited_by_count":190},{"id":"1502.02734","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","created":"2015-02-09","cited_by_count":189},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"1803.09569","title":"On Regularized Losses for Weakly-supervised CNN Segmentation","created":"2018-03-26","cited_by_count":121},{"id":"2204.13317","title":"MMRotate: A Rotated Object Detection Benchmark using PyTorch","created":"2022-04-28","cited_by_count":115},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1804.01346","title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation","created":"2018-04-04","cited_by_count":112},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102},{"id":"1802.00470","title":"Learning random-walk label propagation for weakly-supervised semantic segmentation","created":"2018-02-01","cited_by_count":101},{"id":"1506.03648","title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation","created":"2015-06-11","cited_by_count":100},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"1910.06962","title":"SegSort: Segmentation by Discriminative Sorting of Segments","created":"2019-10-15","cited_by_count":96},{"id":"2306.16623","title":"The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot","created":"2023-06-29","cited_by_count":83},{"id":"2012.03044","title":"Self-Supervised Visual Representation Learning from Hierarchical Grouping","created":"2020-12-05","cited_by_count":63},{"id":"2203.14309","title":"DeepDPM: Deep Clustering With an Unknown Number of Clusters","created":"2022-03-27","cited_by_count":52},{"id":"2304.09324","title":"Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets","created":"2023-04-18","cited_by_count":45},{"id":"2304.10597","title":"Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models","created":"2023-04-20","cited_by_count":44},{"id":"1804.03821","title":"ExFuse: Enhancing Feature Fusion for Semantic Segmentation","created":"2018-04-11","cited_by_count":42},{"id":"2112.00735","title":"Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation","created":"2021-12-01","cited_by_count":33},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24},{"id":"1506.04924","title":"Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation","created":"2015-06-16","cited_by_count":23},{"id":"2305.07586","title":"Knowledge distillation with Segment Anything (SAM) model for Planetary Geological Mapping","created":"2023-05-12","cited_by_count":16},{"id":"2309.16992","title":"Segment Anything Model is a Good Teacher for Local Feature Learning","created":"2023-09-29","cited_by_count":15},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15},{"id":"1909.06861","title":"Online k-means Clustering","created":"2019-09-15","cited_by_count":13},{"id":"2209.13635","title":"Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning","created":"2022-09-27","cited_by_count":3}],"next_cursor":null}