Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite
| Autor: | Trung-Nghia Le, Minh-Triet Tran, Minh-Quan Le, Tan-Cong Nguyen, Tam V. Nguyen, Yubo Cao, Thanh-Toan Do, Khanh-Duy Nguyen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Suite Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition Object (computer science) Computer Graphics and Computer-Aided Design GeneralLiterature_MISCELLANEOUS Image (mathematics) Task (project management) Camouflage Benchmark (computing) Segmentation Artificial intelligence business Software |
| Popis: | 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 TIP acceptance. Project page: https://sites.google.com/view/ltnghia/research/camo_plus_plus |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|