EVer - A Library for Earth Vision Researcher

EVer is a Pytorch-based Python library to simplify the training and inference of the deep learning model in the remote sensing domain.

This is a beta version for research only.

Features

• Common codebase for reproducible research
• Accelerating our Earth Vision research
• Single workflow of "data-module-configs"

Installation

stable version (0.5.0)

pip install ever-beta

nightly version (master)

pip install --upgrade git+https://github.com/Z-Zheng/ever.git

Getting Started

Basic Usage

Projects using EVer

Change Detection (Our Change Family)

• torchange: A Unified Change Representation Learning Benchmark Library [Code]
• (AnyChange) Segment Any Change, NeurIPS 2024 [Paper]
• (Changen) Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process, ICCV 2023 [Paper], [Code]
• (ChangeMask) ChangeMask: Deep Multi-task Encoder-Transformer-Decoder Architecture for Semantic Change Detection, ISPRS P&RS 2022. [Paper]
• (ChangeStar) Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery, ICCV 2021. [Paper], [Project], [Code]
• (ChangeOS) Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: from natural disasters to man-made disasters, RSE 2021. [Paper], [Code]

Segmentation

• FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery, IEEE TPAMI 2023. [Paper], [Code]
• Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery, CVPR 2020. [Paper], [Code]
• Deep multisensor learning for missing-modality all-weather mapping, ISPRS P&RS 2021. [Paper]
• FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery, TGRS 2021. [Paper], [Code]
• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation, NeurIPS 2021 Datasets and Benchmarks. [Paper], [Code/Dataset]

Hyperspectral Image Classification

• FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification, TGRS 2020. [Paper], [Code]

License

EVer is released under the Apache License 2.0.

Copyright (c) Zhuo Zheng. All rights reserved.