Camouflaged Object Segmentation
Camouflaged Object (CAMO) dataset specifically designed for the task of camouflaged object segmentation. We focus on two categories, i.e., naturally camouflaged objects and artificially camouflaged objects, which usually correspond to animals and humans in the real world, respectively.
Camouflaged object images consists of 1250 images (1000 images for the training set and 250 images for the testing set). Non-camouflaged object images are collected from the MS-COCO dataset (1000 images for the training set and 250 images for the testing set).
CAMO has objectness mask ground-truth.
Our new CAMO++ dataset with instance-level annotations is here.
Is your technique missing although it's published? Let me know and I'll add it.
Methods
Download
Datasets: [CAMO] [Evaluation Code]
Code: [ANet] [MirrorNet]
If you use our datasets, codes or results, please cite the following publications:
Publications
Trung-Nghia Le, Tam V. Nguyen, Zhongliang Nie, Minh-Triet Tran, Akihiro Sugimoto, "Anabranch Network for Camouflaged Object Segmentation", Journal of Computer Vision and Image Understanding (CVIU), 2019. [PDF]
Jinnan Yan, Trung-Nghia Le, Khanh-Duy Nguyen, Minh-Triet Tran, Thanh-Toan Do, Tam V. Nguyen, "MirrorNet: Bio-Inspired Camouflaged Object Segmentation", IEEE Access, 2021. [PDF]
License
Our data and code are published under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License. You must not use this work for commercial purposes. If you alter or build upon this work, you have to distribute the resulting work only under the same license. If you are interested in commercial usage, please contact us.