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

• Published in: IEEE transactions on image processing Vol. 31; pp. 287 - 300
• Main Authors: Le, Trung-Nghia, Cao, Yubo, Nguyen, Tan-Cong, Le, Minh-Quan, Nguyen, Khanh-Duy, Do, Thanh-Toan, Tran, Minh-Triet, Nguyen, Tam V.
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: benchmark suite; Benchmark testing; Benchmarks; Camouflage; camouflage dataset; Camouflaged instance segmentation; Datasets; Image color analysis; Image segmentation; in-the-wild image; Instance segmentation; multimodal learning; Object segmentation; Semantics; State-of-the-art reviews; Task analysis; Urban areas
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2021.3130490

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.