Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these meth…

A personal investigative project to track the latest progress in the field of multi-modal object tracking.

A Large Multimodal Model for Remote Sensing Change Description

SAM4SS: Tailoring SAM and SAM2 for Semantic Segmentation

Official Implementation of ECCV2024 paper: SLAck

Tiny Object Detection in Remote Sensing Images Based on Object Reconstruction and Multiple Receptive Field Adaptive Feature Enhancement (IEEE TGRS 2024)

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

[JAG 2024] REPS: Rotation Equivariant Siamese Network Enhanced by Probability Segmentation for Satellite Video Tracking

[Datasets] LMOD: a large-scale and multiclass object detection dataset for satellite videos

[ISPRS 2024] Satellite Video Single Object Tracking: A Systematic Review and An Oriented Object Tracking Benchmark

Masked Angle-Aware Autoencoder for Remote Sensing Images (ECCV 2024)

The Most Faithful Implementation of Segment Anything (SAM) in 3D

[AAAI 2024] EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

Official repo for "SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing"

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

🔖 Curated list of video object segmentation (VOS) papers, datasets, and projects.

image registration related books, papers, videos, and toolboxes

Datasets for deep learning with satellite & aerial imagery

The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Segment Anything in High Quality [NeurIPS 2023]

🛰️ List of satellite image training datasets with annotations for computer vision and deep learning

🛰️ List of satellite image training datasets with annotations for computer vision and deep learning

A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding

SSL4EO-S12: a large-scale dataset for self-supervised learning in Earth observation