# CATNet **Repository Path**: lqhg/CATNet ## Basic Information - **Project Name**: CATNet - **Description**: No description available - **Primary Language**: Unknown - **License**: GPL-3.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2024-10-21 - **Last Updated**: 2024-10-21 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # Context Aggregation Network [![arXiv](https://badgen.net/badge/arXiv/2111.11057/red?cache=300)](https://arxiv.org/abs/2111.11057) [![License](https://badgen.net/github/license/yeliudev/CATNet?label=License&color=cyan&cache=300)](https://github.com/yeliudev/CATNet/blob/main/LICENSE) This repository maintains the official implementation of the paper **Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images** by [Ye Liu](https://yeliu.dev/), [Huifang Li](https://faculty.whu.edu.cn/show.jsp?n=Huifang%20Li), [Chao Hu](https://orcid.org/0000-0001-6183-9051), [Shuang Luo](https://www.researchgate.net/profile/shuang-luo-6), [Yan Luo](https://www.researchgate.net/profile/Yan_Luo65), and [Chang Wen Chen](https://web.comp.polyu.edu.hk/chencw/), which has been accepted by [TNNLS](https://cis.ieee.org/publications/t-neural-networks-and-learning-systems).

## Installation Please refer to the following environmental settings that we use. You may install these packages by yourself if you meet any problem during automatic installation. - CUDA 11.8 - CUDNN 8.7.0.84 - Python 3.11.3 - PyTorch 2.0.1 - [MMEngine](https://github.com/open-mmlab/mmengine) 0.7.4 - [MMCV](https://github.com/open-mmlab/mmcv) 2.0.0 - [MMDetection](https://github.com/open-mmlab/mmdetection) 3.0.0 - [NNCore](https://github.com/yeliudev/nncore) 0.3.6 ### Install from source 1. Clone the repository from GitHub. ``` git clone https://github.com/yeliudev/CATNet.git cd CATNet ``` 2. Install dependencies. ``` pip install -r requirements.txt ``` 3. Set environment variable ``` export PYTHONPATH=$PWD:$PYTHONPATH ``` ## Getting Started ### Download and prepare the datasets 1. Download the pre-processed datasets. - [iSAID](https://huggingface.co/yeliudev/CATNet/resolve/main/datasets/isaid-9d62d4ad.zip) - [DIOR](https://huggingface.co/yeliudev/CATNet/resolve/main/datasets/dior-b162132d.zip) - [NWPU VHR-10](https://huggingface.co/yeliudev/CATNet/resolve/main/datasets/vhr-79ccc9f3.zip) - [HRSID](https://huggingface.co/yeliudev/CATNet/resolve/main/datasets/hrsid-4e02052e.zip) 2. Prepare the files in the following structure. ``` CATNet ├── configs ├── datasets ├── models ├── tools ├── data │ ├── dior │ │ ├── Annotations │ │ ├── ImageSets │ │ └── JPEGImages │ ├── hrsid │ │ ├── annotations │ │ └── images │ ├── isaid │ │ ├── train │ │ ├── val │ │ └── test │ └── vhr │ ├── annotations │ └── images ├── README.md ├── setup.cfg └── ··· ``` ### Train a model Run the following command to train a model using a specified config. ``` mim train mmdet --gpus 4 --launcher pytorch ``` > If an `out-of-memory` error occurs on iSAID dataset, please uncomment [L22-L24](https://github.com/yeliudev/CATNet/blob/main/datasets/isaid.py#L22:L24) in the dataset code and try again. This will filter out a few images with more than 1,000 objects, largely reducing the memory cost. ### Test a model and evaluate results Run the following command to test a model and evaluate results. ``` mim test mmdet --checkpoint --gpus 4 --launcher pytorch ``` ## Model Zoo We provide multiple pre-trained models here. All the models are trained using 4 NVIDIA A100 GPUs and are evaluated using the default metrics of the datasets.
Dataset Model Backbone Schd Aug Performance Download
BBox AP Mask AP
iSAID CAT Mask R-CNN ResNet-50 3x ✗ 45.1 37.2 model | metrics
CAT Mask R-CNN ResNet-50 3x ✓ 47.7 39.2 model | metrics
DIOR CATNet ResNet-50 3x ✗ 74.0 — model | metrics
CATNet ResNet-50 3x ✓ 78.2 — model | metrics
CAT R-CNN ResNet-50 3x ✗ 75.8 — model | metrics
CAT R-CNN ResNet-50 3x ✓ 80.6 — model | metrics
NWPU
VHR-10 		CAT Mask R-CNN ResNet-50 6x ✗ 71.0 69.3 model | metrics
CAT Mask R-CNN ResNet-50 6x ✓ 72.4 70.7 model | metrics
HRSID CAT Mask R-CNN ResNet-50 6x ✗ 70.9 57.6 model | metrics
CAT Mask R-CNN ResNet-50 6x ✓ 72.0 59.6 model | metrics
## Citation If you find this project useful for your research, please kindly cite our paper. ```bibtex @article{liu2024learning, title={Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images}, author={Liu, Ye and Li, Huifang and Hu, Chao and Luo, Shuang and Luo, Yan and Chen, Chang Wen}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2024} } ```