{"list":"other","total":59,"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":"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"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":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210},{"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":"2403.11703","title":"LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images","created":"2024-03-18","cited_by_count":195},{"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":"2003.07325","title":"Domain Adaptive Ensemble Learning","created":"2020-03-16","cited_by_count":156},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"1809.08545","title":"Bounding Box Regression with Uncertainty for Accurate Object Detection","created":"2018-09-23","cited_by_count":143},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138},{"id":"2206.13188","title":"Self-supervised Learning in Remote Sensing: A Review","created":"2022-06-27","cited_by_count":137},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117},{"id":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98},{"id":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93},{"id":"2006.10027","title":"Deep Learning Meets SAR","created":"2020-06-17","cited_by_count":60},{"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":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48},{"id":"2206.04664","title":"On Data Scaling in Masked Image Modeling","created":"2022-06-09","cited_by_count":46},{"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":"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":"2303.02416","title":"PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling","created":"2023-03-04","cited_by_count":28},{"id":"2007.02106","title":"Automatic Target Recognition on Synthetic Aperture Radar Imagery: A Survey","created":"2020-07-04","cited_by_count":18},{"id":"2110.14144","title":"Physically Explainable CNN for SAR Image Classification","created":"2021-10-27","cited_by_count":16},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"2404.03595","title":"DiffDet4SAR: Diffusion-based Aircraft Target Detection Network for SAR Images","created":"2024-04-04","cited_by_count":15},{"id":"2209.04779","title":"Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense","created":"2022-09-11","cited_by_count":14},{"id":"2207.06985","title":"ObjectBox: From Centers to Boxes for Anchor-Free Object Detection","created":"2022-07-14","cited_by_count":12},{"id":"2304.00668","title":"Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR","created":"2023-04-03","cited_by_count":9},{"id":"2304.03550","title":"Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition","created":"2023-04-07","cited_by_count":6},{"id":"2308.05464","title":"Global in Local: A Convolutional Transformer for SAR ATR FSL","created":"2023-08-10","cited_by_count":5},{"id":"2308.10911","title":"Crucial Feature Capture and Discrimination for Limited Training Data SAR ATR","created":"2023-08-20","cited_by_count":4},{"id":"2403.03527","title":"LDSF: Lightweight Dual-Stream Framework for SAR Target Recognition by Coupling Local Electromagnetic Scattering Features and Global Visual Features","created":"2024-03-06","cited_by_count":3}],"next_cursor":null}