English

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

Computer Vision and Pattern Recognition 2021-12-14 v4

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: https://sites.google.com/view/ltnghia/research/camo_plus_plus

Keywords

Cite

@article{arxiv.2103.17123,
  title  = {Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite},
  author = {Trung-Nghia Le and Yubo Cao and Tan-Cong Nguyen and Minh-Quan Le and Khanh-Duy Nguyen and Thanh-Toan Do and Minh-Triet Tran and Tam V. Nguyen},
  journal= {arXiv preprint arXiv:2103.17123},
  year   = {2021}
}

Comments

TIP acceptance. Project page: https://sites.google.com/view/ltnghia/research/camo_plus_plus

R2 v1 2026-06-24T00:44:17.419Z