DMRA_RGBD-SOD

Code repository for our paper entilted "Depth-induced Multi-scale Recurrent Attention Network for Saliency Detection" accepted at ICCV 2019 (poster).

Overall

The proposed Dataset

• Dataset: DUTLF

1. Our DUTLF family consists of DUTLF-MV, DUTLF-FS, DUTLF-Depth.
2. The dataset will be expanded to 4000 about real scenes.
3. We are working on it and will make it publicly available soon.

• Dataset: DUTLF-Depth

1. The dataset is part of DUTLF dataset captured by Lytro camera, and we selected a more accurate 1200 depth map pairs for more accurate RGB-D saliency detection.
2. We create a large scale RGB-D dataset(DUTLF-Depth) with 1200 paired images containing more complex scenarios, such as multiple or transparent objects, similar foreground and background, complex background, low-intensity environment. This challenging dataset can contribute to comprehensively evaluating saliency models.

• The dataset link can be found here. And we split the dataset including 800 training set and 400 test set.

DMRA Code

> Requirment

• pytorch 0.3.0+
• torchvision
• PIL
• numpy

> Usage

1. Clone the repo

git clone https://github.com/jiwei0921/DMRA.git
cd DMRA/

2. Train/Test

• test
  Download related dataset link, and set the param '--phase' as "test" and '--param' as 'True' in demo.py. Meanwhile, you need to set dataset path and checkpoint name correctly.

python demo.py

• train
  Our train-augment dataset link [ fetch code haxl ] / train-ori dataset, and set the param '--phase' as "train" and '--param' as 'True'(loading checkpoint) or 'False'(no loading checkpoint) in demo.py. Meanwhile, you need to set dataset path and checkpoint name correctly.

python demo.py

> Training info and pre-trained models for DMRA

To better understand, we retrain our network and record some detailed training details as well as corresponding pre-trained models.

• Tips: The results of the paper shall prevail. Because of the randomness of the training process, the results fluctuated slightly.

> Results

| DUTLF-Depth | | NJUD | | NLPR | | STEREO | | LFSD | | RGBD135 | | SSD |

• Note: For evaluation, all results are implemented on this ready-to-use toolbox.
• SIP results: This is test results on SIP dataset, and fetch code is 'fi5h'.

> Related RGB-D Saliency Datasets

All common RGB-D Saliency Datasets we collected are shared in ready-to-use manner.

• The web link is here.

If you think this work is helpful, please cite

@inproceedings{piao2019depth,
  title={Depth-induced multi-scale recurrent attention network for saliency detection},
  author={Piao, Yongri and Ji, Wei and Li, Jingjing and Zhang, Miao and Lu, Huchuan},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={7254--7263},
  year={2019}
}

Related SOTA RGB-D methods' results on our dataset

Meanwhile, we also provide other state-of-the-art RGB-D methods' results on our proposed dataset, and you can directly download their results (All results,2gs2).

• Thanks for related authors to provide the code or results, particularly, Deng-ping Fan, Hao Chen, Chun-biao Zhu, etc.

Contact Us

If you have any questions, please contact us ( [email protected] or [email protected] ).