Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite

Author(s)

• Trung-Nghia Le, National Institute of Informatics
• Yubo Cao, University of Dayton
• Tan-Cong Nguyen, Vietnam National University
• Minh-Quan Le, Vietnam National University
• Khanh-Duy Nguyen, Vietnam National University
• Thanh-Toan Do, Monash University
• Minh-Triet Tran, Vietnam National University
• Tam V. Nguyen, University of DaytonFollow

Document Type

Article

Publication Date

12-2-2021

Publication Source

IEEE Transactions on Image Processing

Abstract

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths. We also provide a benchmark suite for the task of camouflaged instance segmentation. In particular, we present an extensive evaluation of state-of-the-art instance segmentation methods on our newly constructed CAMO++ dataset in various scenarios. We also present a camouflage fusion learning (CFL) framework for camouflaged instance segmentation to further improve the performance of state-of-the-art methods. The dataset, model, evaluation suite, and benchmark will be made publicly available on our project page.

Inclusive pages

287-300

ISBN/ISSN

1057-7149

Publisher

IEEE xplore

Volume

31

Keywords

Image segmentation, Task analysis, Benchmark testing, Object segmentation, Image color analysis, Urban areas, Semantics, Camouflaged instance segmentation, in-the-wild image, camouflage dataset, benchmark suite, multimodal learning

eCommons Citation

Le, Trung-Nghia; Cao, Yubo; Nguyen, Tan-Cong; Le, Minh-Quan; Nguyen, Khanh-Duy; Do, Thanh-Toan; Tran, Minh-Triet; and Nguyen, Tam V., "Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite" (2021). Computer Science Faculty Publications. 207.
https://ecommons.udayton.edu/cps_fac_pub/207