{"list":"other","total":67,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"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":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"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":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"1902.06148","title":"BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding","created":"2019-02-16","cited_by_count":234},{"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":"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":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2310.18660","title":"Foundation Models for Generalist Geospatial Artificial Intelligence","created":"2023-10-28","cited_by_count":149},{"id":"2206.13188","title":"Self-supervised Learning in Remote Sensing: A Review","created":"2022-06-27","cited_by_count":137},{"id":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125},{"id":"2306.03831","title":"GEO-Bench: Toward Foundation Models for Earth Monitoring","created":"2023-06-06","cited_by_count":124},{"id":"2203.04181","title":"Selective-Supervised Contrastive Learning with Noisy Labels","created":"2022-03-08","cited_by_count":112},{"id":"1805.02855","title":"Tile2Vec: Unsupervised representation learning for spatially distributed data","created":"2018-05-08","cited_by_count":110},{"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":"2403.15356","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","created":"2024-03-22","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":"2105.07921","title":"BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval","created":"2021-05-17","cited_by_count":92},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2110.04770","title":"Weakly Supervised Contrastive Learning","created":"2021-10-10","cited_by_count":81},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2204.13207","title":"Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework","created":"2022-04-27","cited_by_count":59},{"id":"2306.09424","title":"SSL4EO-L: Datasets and Foundation Models for Landsat Imagery","created":"2023-06-15","cited_by_count":49},{"id":"2310.18653","title":"Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing","created":"2023-10-28","cited_by_count":48},{"id":"1911.06721","title":"In-domain representation learning for remote sensing","created":"2019-11-15","cited_by_count":41},{"id":"2202.04639","title":"Point-Level Region Contrast for Object Detection Pre-Training","created":"2022-02-09","cited_by_count":41},{"id":"2107.05276","title":"Geographical Knowledge-driven Representation Learning for Remote Sensing Images","created":"2021-07-12","cited_by_count":37},{"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":"2405.04285","title":"On the Foundations of Earth and Climate Foundation Models","created":"2024-05-07","cited_by_count":33},{"id":"2007.09852","title":"Multi-label Contrastive Predictive Coding","created":"2020-07-20","cited_by_count":32},{"id":"2105.03953","title":"Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation","created":"2021-05-09","cited_by_count":29},{"id":"2107.08712","title":"Exploring Set Similarity for Dense Self-supervised Representation Learning","created":"2021-07-19","cited_by_count":29},{"id":"2209.00314","title":"Self-Supervised Pretraining for 2D Medical Image Segmentation","created":"2022-09-01","cited_by_count":24},{"id":"2211.08129","title":"Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works","created":"2022-11-15","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":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18},{"id":"2308.03286","title":"Multi-Label Self-Supervised Learning with Scene Images","created":"2023-08-07","cited_by_count":17},{"id":"2301.00363","title":"Mapping smallholder cashew plantations to inform sustainable tree crop expansion in Benin","created":"2023-01-01","cited_by_count":10}],"next_cursor":null}