Home

Awesome

(CVPR 2022) Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

license: mit LAST COMMIT ISSUES STARS ARXIV PAPER ARXIV PAPER

@inproceedings{ZoomNet-CVPR2022,
	title     = {Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection},
	author    = {Pang, Youwei and Zhao, Xiaoqi and Xiang, Tian-Zhu and Zhang, Lihe and Lu, Huchuan},
	booktitle = CVPR,
	year      = {2022}
}

Extensions to the conference version can be found: https://github.com/lartpang/ZoomNeXt.

Changelog

Usage

Dependencies

Some core dependencies:

More details can be found in <./requirements.txt>

Datasets

More details can be found at:

Training

You can use our default configuration, like this:

$ python main.py --model-name=ZoomNet --config=configs/zoomnet/zoomnet.py --datasets-info ./configs/_base_/dataset/dataset_configs.json --info demo

or use our launcher script to start the one command in commands.txt on GPU 1:

$ python tools/run_it.py --interpreter 'abs_path' --cmd-pool tools/commands.txt  --gpu-pool 1 --verbose --max-workers 1

If you want to launch multiple commands, you can use it like this:

  1. Add your commands into the tools/commands.txt.
  2. python tools/run_it.py --interpreter 'abs_path' --cmd-pool tools/commands.txt --gpu-pool <gpu indices> --verbose --max-workers max_workers

NOTE:

Testing

TaskWeightsResults
CODGitHub Release LinkGitHub Release Link
SODGitHub Release LinkGitHub Release Link

For ease of use, we create a test.py script and a use case in the form of a shell script test.sh.

$ sudo chmod +x ./test.sh
$ ./test.sh 0  # on gpu 0

Method Comparisons

Paper Details

Method Detials

Comparison

Camouflaged Object Detection

Salient Object Detection