Data

Tools

Indexes

Applications

Experiments

Open Source Science

bafe-net

https://github.com/grokcv/bafe-net

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: GrokCV
  • License: apache-2.0
  • Language: Python
  • Default Branch: master
  • Size: 2.52 MB
Statistics
  • Stars: 17
  • Watchers: 1
  • Forks: 0
  • Open Issues: 2
  • Releases: 0
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection With Sky-Annotated Dataset

This repository is the official implementation of BAFE-Net

Paper link: Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection With Sky-Annotated Dataset

DenseSIRST

DenseSIRST Datasets: https://github.com/GrokCV/DenseSIRST

DenseSIRST

You can download our DenseSIRST dataset from Google Drive.

For both training and inference, the following dataset structure is required:

angular2html |- data |- SIRSTdevkit |-PNGImages |-Misc_1.png ...... |-SIRST |-BBox |-Misc_1.xml ...... |-BinaryMask |-Misc_1_pixels0.png |-Misc_1.xml ...... |-PaletteMask |-Misc_1.png ...... |-Point_label |-Misc_1_pixels0.txt ...... |-SkySeg |-BinaryMask |-Misc_1_pixels0.png |-Misc_1.xml ...... |-PaletteMask |-Misc_1.png ...... |-Splits |-train_v2.txt |-test_v2.txt ......

  • PNGImages is the folder for storing all images.
  • SIRST and SkySeg are folders for storing annotation files.
    • SIRST corresponds to infrared small targets.
    • SkySeg corresponds to sky segmentation.

Please make sure that the path of your data set is consistent with the data_root in configs/detection/_base_/datasets/sirst_det_seg_voc_skycp.py

Model Zoo and Benchmark

Checkpoint and Train log: Google Drive.

Leaderboard

| Method | Backbone | mAP07↑ | recall07↑ | mAP12↑ | recall12↑ | Flops↓ | Params↓ | | - | - | - | - | - | - | - | - | | One-stage | | | | | | | | | | SSD | VGG16 | 87.552G | 23.746M | 0.211 | 0.421 | 0.178 | 0.424 | | RetinaNet | ResNet50 | 52.203G | 36.330M | 0.114 | 0.510 | 0.086 | 0.523 | | YOLOv3 | Darknet | 50.002G | 61.949M | 0.233 | 0.424 | 0.207 | 0.413 | | CenterNet | ResNet50 | 50.278G | 32.111M | 0.138 | 0.316 | 0.124 | 0.317 | | FCOS | ResNet50 | 50.291G | 32.113M | 0.232 | 0.315 | 0.204 | 0.324 | | ATSS | ResNet50 | 51.504G | 32.113M | 0.248 | 0.327 | 0.202 | 0.326 | | CentripetalNet | HourglassNet | 0.491T | 0.206G | 0.244 | 0.259 | 0.201 | 0.244 | | AutoAssign | ResNet50 | 50.555G | 36.244M | 0.255 | 0.354 | 0.180 | 0.314 | | GFL | ResNet50 | 52.296G | 32.258M | 0.264 | 0.367 | 0.230 | 0.317 | | PAA | ResNet50 | 51.504G | 32.113M | 0.255 | 0.545 | 0.228 | 0.551 | | VFNet | ResNet50 | 48.317G | 32.709M | 0.253 | 0.336 | 0.214 | 0.336 | | PVT-T | PVT | 41.623G | 21.325M | 0.109 | 0.481 | 0.093 | 0.501 | | YOLOF | ResNet50 | 25.076G | 42.339M | 0.091 | 0.009 | 0.002 | 0.009 | | YOLOX | CSPDarknet | 8.578G | 8.968M | 0.210 | 0.341 | 0.180 | 0.331 | | TOOD | ResNet50 | 50.456G | 32.018M | 0.256 | 0.355 | 0.226 | 0.342 | | DyHead | ResNet50 | 27.866G | 38.890M | 0.249 | 0.335 | 0.189 | 0.328 | | DDOD | ResNet50 | 46.514G | 32.378M | 0.253 | 0.335 | 0.230 | 0.351 | | RTMDet | CSPNeXt | 51.278G | 52.316M | 0.229 | 0.349 | 0.212 | 0.350 | | EfficientDet | EfficientNet | 34.686G | 18.320M | 0.146 | 0.464 | 0.094 | 0.517 | | Two-stage | | | | | | | | | Faster R-CNN | ResNet50 | 0.759T | 33.035M | 0.091 | 0.022 | 0.015 | 0.029 | | Cascade R-CNN | ResNet50 | 90.978G | 69.152M | 0.136 | 0.188 | 0.139 | 0.194 | | Grid R-CNN | ResNet50 | 0.177T | 64.467M | 0.156 | 0.122 | 0.104 | 0.190 | | Libra R-CNN | ResNet50 | 63.990G | 41.611M | 0.141 | 0.142 | 0.085 | 0.120 | | TridentNet | ResNet50 | 0.759T | 33.035M | 0.091 | 0.009 | 0.014 | 0.021 | | SABL | ResNet50 | 0.125T | 42.213M | 0.124 | 0.104 | 0.104 | 0.171 | | Dynamic R-CNN | ResNet50 | 63.179G | 41.348M | 0.184 | 0.235 | 0.111 | 0.190 | | End2End | | | | | | | | | DETR | ResNet50 | 24.940G | 41.555M | 0.000 | 0.000 | 0.000 | 0.000 | | Sparse R-CNN | ResNet50 | 45.274G | 0.106G | 0.183 | 0.572 | 0.154 | 0.614 | | Deformable DETR | ResNet50 | 51.772G | 40.099M | 0.024 | 0.016 | 0.018 | 0.197 | | Conditional DETR | ResNet50 | 27.143G | 40.297M | 0.000 | 0.000 | 0.000 | 0.001 | | DAB-DETR | ResNet50 | 28.939G | 43.702M | 0.005 | 0.054 | 0.000 | 0.001 | | BAFE-Net (Ours) | ResNet18 | 57.654G | 22.31M | 0.283 | 0.335 | 0.233 | 0.325 | | BAFE-Net (Ours) | ResNet50 | 71.639G | 35.626M | 0.274 | 0.342 | 0.248 | 0.338 |

BAFE-Net

BAFE-Net

Installation

Step 1: Create a conda environment

shell $ conda create --name deepir python=3.9 $ conda activate deepir

Step 2: Install PyTorch

shell $ conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

Step 3: Install OpenMMLab Codebases

shell pip install -U openmim mim install mmengine mim install "mmcv>=2.0.0" mim install "mmdet>=3.0.0" pip install "mmsegmentation>=1.0.0" pip install dadaptation

Step 4: Install deepir

shell $ python setup.py develop

Note: make sure you have cd to the root directory of deepinfrared

shell $ git clone git@github.com:GrokCV/BAFE-Net.git $ cd BAFE-Net

Train

Single GPU Training

shell $ CUDA_VISIBLE_DEVICES=0 python train.py <CONFIG_FILE>

For example:

shell $ CUDA_VISIBLE_DEVICES=0 python tools/train_det.py configs/detection/fcos_changer_seg/fcos_changer_seg_r50-caffe_fpn_gn-head_1x_densesirst.py

Multi GPU Training

shell $ CUDA_VISIBLE_DEVICES=0,1 torchrun --nproc_per_node=2 train.py <CONFIG_FILE>

For example:

shell $ CUDA_VISIBLE_DEVICES=0,1 torchrun --nproc_per_node=2 ./tools/train_det.py configs/detection/fcos_changer_seg/fcos_changer_seg_r50-caffe_fpn_gn-head_1x_densesirst.py

Test

shell $ CUDA_VISIBLE_DEVICES=0 python test.py <CONFIG_FILE> <SEG_CHECKPOINT_FILE>

For example:

shell $ CUDA_VISIBLE_DEVICES=0 python tools/test_det.py configs/detection/fcos_changer_seg/fcos_changer_seg_r50-caffe_fpn_gn-head_1x_densesirst.py work_dirs/fcos_changer_seg_r50-caffe_fpn_gn-head_1x_densesirst/20240719_162542/best_pascal_voc_mAP_epoch_8.pth

If you want to visualize the result, you only add --show at the end of the above command.

The default image save path is under . You can use --work-dir to specify the test log path, and the image save path is under this path by default. Of course, you can also use --show-dir to specify the image save path.

Citation

If you use our dataset or code in your research, please cite this project.

```bibtex @article{xiao2024bafenet, title={Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection With Sky-Annotated Dataset}, author={Mengxuan Xiao and Qun Dai and Yiming Zhu and Kehua Guo and Huan Wang and Xiangbo Shu and Jian Yang and Yimian Dai}, year={2024}, journal={arXiv preprint arXiv:2407.20078}, }

@article{dai2023one, title={One-stage cascade refinement networks for infrared small target detection}, author={Dai, Yimian and Li, Xiang and Zhou, Fei and Qian, Yulei and Chen, Yaohong and Yang, Jian}, journal={IEEE Transactions on Geoscience and Remote Sensing}, volume={61}, pages={1--17}, year={2023}, } ```

Owner

  • Name: GrokCV
  • Login: GrokCV
  • Kind: organization

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "DeepInfrared Contributors"
title: "DeepInfrared Toolbox and Benchmark"
date-released: 2022-12-01
url: "https://github.com/YimianDai/open-deepinfrared"
license: Apache-2.0

GitHub Events

Total
  • Issues event: 6
  • Watch event: 13
  • Issue comment event: 6
  • Push event: 12
Last Year
  • Issues event: 6
  • Watch event: 13
  • Issue comment event: 6
  • Push event: 12

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • boboyu12138 (1)
  • HTsummer (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

deepir.egg-info/requires.txt pypi
  • asynctest *
  • cityscapesscripts *
  • codecov *
  • cython *
  • flake8 *
  • imagecorruptions *
  • instaboostfast *
  • interrogate *
  • isort ==4.3.21
  • kwarray *
  • matplotlib *
  • memory_profiler *
  • mmcv <2.1.0,>=2.0.0rc4
  • mmengine <1.0.0,>=0.7.1
  • mmtrack *
  • numpy *
  • onnx ==1.7.0
  • onnxruntime >=1.8.0
  • parameterized *
  • protobuf <=3.20.1
  • psutil *
  • pycocotools *
  • pytest *
  • scikit-learn *
  • scipy *
  • shapely *
  • six *
  • terminaltables *
  • ubelt *
  • xdoctest >=0.10.0
  • yapf *
requirements/albu.txt pypi
  • albumentations >=0.3.2
requirements/build.txt pypi
  • cython *
  • numpy *
requirements/docs.txt pypi
  • docutils ==0.16.0
  • myst-parser *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
  • sphinx_rtd_theme ==0.5.2
requirements/mminstall.txt pypi
  • mmcv >=2.0.0rc4,<2.1.0
  • mmengine >=0.7.1,<1.0.0
requirements/optional.txt pypi
  • cityscapesscripts *
  • imagecorruptions *
  • scikit-learn *
requirements/readthedocs.txt pypi
  • mmcv >=2.0.0rc4,<2.1.0
  • mmengine >=0.7.1,<1.0.0
  • scipy *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • matplotlib *
  • numpy *
  • pycocotools *
  • scipy *
  • shapely *
  • six *
  • terminaltables *
requirements/tests.txt pypi
  • asynctest * test
  • cityscapesscripts * test
  • codecov * test
  • flake8 * test
  • imagecorruptions * test
  • instaboostfast * test
  • interrogate * test
  • isort ==4.3.21 test
  • kwarray * test
  • memory_profiler * test
  • onnx ==1.7.0 test
  • onnxruntime >=1.8.0 test
  • parameterized * test
  • protobuf <=3.20.1 test
  • psutil * test
  • pytest * test
  • ubelt * test
  • xdoctest >=0.10.0 test
  • yapf * test
requirements.txt pypi
setup.py pypi