{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"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":"1807.01232","title":"SpaceNet: A Remote Sensing Dataset and Challenge Series","created":"2018-07-03","cited_by_count":179},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"1810.08468","title":"Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks","created":"2018-10-19","cited_by_count":110},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"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":"2403.05419","title":"Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery","created":"2024-03-08","cited_by_count":83},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77},{"id":"2412.14123","title":"AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities","created":"2024-12-18","cited_by_count":74},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2304.09670","title":"CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding","created":"2023-04-19","cited_by_count":48},{"id":"2205.13137","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","created":"2022-05-26","cited_by_count":47},{"id":"2401.15855","title":"Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing","created":"2024-01-29","cited_by_count":47},{"id":"2404.08489","title":"SpectralMamba: Efficient Mamba for Hyperspectral Image Classification","created":"2024-04-12","cited_by_count":36},{"id":"2204.08227","title":"The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training","created":"2022-04-18","cited_by_count":33},{"id":"2206.00790","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","created":"2022-06-01","cited_by_count":27},{"id":"2404.18401","title":"Spectral-Spatial Mamba for Hyperspectral Image Classification","created":"2024-04-29","cited_by_count":24},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22},{"id":"2408.01946","title":"Masked Angle-Aware Autoencoder for Remote Sensing Images","created":"2024-08-04","cited_by_count":22},{"id":"2203.12054","title":"Self-supervision through Random Segments with Autoregressive Coding (RandSAC)","created":"2022-03-22","cited_by_count":16},{"id":"2212.01610","title":"Exploring Stochastic Autoregressive Image Modeling for Visual Representation","created":"2022-12-03","cited_by_count":14},{"id":"2410.00871","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","created":"2024-10-01","cited_by_count":12},{"id":"2403.08271","title":"Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification","created":"2024-03-13","cited_by_count":8},{"id":"2305.15248","title":"Delving Deeper into Data Scaling in Masked Image Modeling","created":"2023-05-24","cited_by_count":5}],"next_cursor":null}