{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"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":"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":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184},{"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":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2210.02885","title":"RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank","created":"2022-10-05","cited_by_count":153},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151},{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2412.02732","title":"Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications","created":"2024-12-03","cited_by_count":144},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"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":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104},{"id":"2304.14065","title":"Lightweight, Pre-trained Transformers for Remote Sensing Timeseries","created":"2023-04-27","cited_by_count":103},{"id":"2204.08322","title":"A high-resolution canopy height model of the Earth","created":"2022-04-13","cited_by_count":91},{"id":"2010.08168","title":"A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery","created":"2020-10-16","cited_by_count":88},{"id":"2211.07044","title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","created":"2022-11-13","cited_by_count":84},{"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":"2410.16602","title":"Foundation Models for Remote Sensing and Earth Observation: A Survey","created":"2024-10-22","cited_by_count":70},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62},{"id":"2304.07213","title":"Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar","created":"2023-04-14","cited_by_count":60},{"id":"2104.07070","title":"Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding","created":"2021-04-14","cited_by_count":58},{"id":"2007.00586","title":"Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series","created":"2020-07-01","cited_by_count":55},{"id":"2112.01715","title":"Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks","created":"2021-12-03","cited_by_count":49},{"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":"2310.18653","title":"Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing","created":"2023-10-28","cited_by_count":48},{"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":"2311.15153","title":"Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture","created":"2023-11-26","cited_by_count":46},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46},{"id":"2408.08447","title":"SpectralEarth: Training Hyperspectral Foundation Models at Scale","created":"2024-08-15","cited_by_count":42},{"id":"2204.05381","title":"Self-supervised Vision Transformers for Joint SAR-optical Representation Learning","created":"2022-04-11","cited_by_count":40},{"id":"2305.02034","title":"SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model","created":"2023-05-03","cited_by_count":38},{"id":"2107.05276","title":"Geographical Knowledge-driven Representation Learning for Remote Sensing Images","created":"2021-07-12","cited_by_count":37},{"id":"2406.17998","title":"Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model","created":"2024-06-26","cited_by_count":37},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36},{"id":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35},{"id":"2401.07527","title":"One for All: Toward Unified Foundation Models for Earth Vision","created":"2024-01-15","cited_by_count":34},{"id":"2401.08083","title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification","created":"2024-01-16","cited_by_count":29},{"id":"2312.02199","title":"USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery","created":"2023-12-02","cited_by_count":28},{"id":"2405.20462","title":"Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining","created":"2024-05-30","cited_by_count":28},{"id":"2402.03631","title":"CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model","created":"2024-02-06","cited_by_count":27},{"id":"2111.11067","title":"Semi-Supervised Vision Transformers","created":"2021-11-22","cited_by_count":24},{"id":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24},{"id":"2207.03860","title":"Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain","created":"2022-07-08","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":"2205.02049","title":"Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images","created":"2022-05-04","cited_by_count":20},{"id":"2303.06670","title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","created":"2023-03-12","cited_by_count":20},{"id":"2408.11000","title":"SenPa-MAE: Sensor Parameter Aware Masked Autoencoder for Multi-Satellite Self-Supervised Pretraining","created":"2024-08-20","cited_by_count":18},{"id":"2503.21841","title":"HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery","created":"2025-03-27","cited_by_count":17},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"2504.03166","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","created":"2025-04-04","cited_by_count":16},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15},{"id":"2401.05093","title":"SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image","created":"2024-01-10","cited_by_count":14},{"id":"2412.14428","title":"WildSAT: Learning Satellite Image Representations from Wildlife Observations","created":"2024-12-19","cited_by_count":13},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12},{"id":"2406.08079","title":"A$^{2}$-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder","created":"2024-06-12","cited_by_count":11},{"id":"2410.19965","title":"OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery","created":"2024-10-25","cited_by_count":11},{"id":"2411.17984","title":"RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model","created":"2024-11-27","cited_by_count":11},{"id":"2412.19237","title":"SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing","created":"2024-12-26","cited_by_count":11},{"id":"2503.10392","title":"RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing","created":"2025-03-13","cited_by_count":11},{"id":"2409.19439","title":"Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery","created":"2024-09-28","cited_by_count":10},{"id":"2501.19328","title":"Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation","created":"2025-01-31","cited_by_count":10},{"id":"2503.07890","title":"Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?","created":"2025-03-10","cited_by_count":10},{"id":"2310.00022","title":"CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding","created":"2023-09-28","cited_by_count":9},{"id":"2312.02151","title":"Guarding Barlow Twins Against Overfitting with Mixed Samples","created":"2023-12-04","cited_by_count":8},{"id":"2411.17000","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","created":"2024-11-26","cited_by_count":7},{"id":"2107.07431","title":"High carbon stock mapping at large scale with optical satellite imagery and spaceborne LIDAR","created":"2021-07-15","cited_by_count":6},{"id":"2411.14354","title":"Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas","created":"2024-11-21","cited_by_count":6},{"id":"2406.14775","title":"Machine Learning Global Simulation of Nonlocal Gravity Wave Propagation","created":"2024-06-20","cited_by_count":5},{"id":"2501.10600","title":"High Resolution Tree Height Mapping of the Amazon Forest using Planet NICFI Images and LiDAR-Informed U-Net Model","created":"2025-01-17","cited_by_count":5},{"id":"2502.00435","title":"SatMamba: Development of Foundation Models for Remote Sensing Imagery Using State Space Models","created":"2025-02-01","cited_by_count":5},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","cited_by_count":4},{"id":"2406.07032","title":"RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks","created":"2024-06-11","cited_by_count":4},{"id":"2312.16385","title":"Analytical Insight of Earth: A Cloud-Platform of Intelligent Computing for Geospatial Big Data","created":"2023-12-27","cited_by_count":3},{"id":"2503.11051","title":"Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning","created":"2025-03-14","cited_by_count":3},{"id":"2407.19660","title":"Towards Knowledge Guided Pretraining Approaches for Multimodal Foundation Models: Applications in Remote Sensing","created":"2024-07-29","cited_by_count":2},{"id":"2411.06091","title":"Pattern Integration and Enhancement Vision Transformer for Self-Supervised Learning in Remote Sensing","created":"2024-11-09","cited_by_count":2}],"next_cursor":null}