CamouFinder: Finding Camouflaged Instances in Images

Author(s)

• Trung-Nghia Le, National Institute of Informatics
• Vuong Nguyen, Vietnam National University
• Cong Le, Vietnam National University
• Tan-Cong Nguyen, Vietnam National University
• Minh-Triet Tran, Vietnam National University
• Tam Van Nguyen, University of DaytonFollow

Document Type

Conference Paper

Publication Date

5-18-2021

Publication Source

Proceedings of the AAAI Conference on Artificial Intelligence

Abstract

In this paper, we investigate the interesting yet challenging problem of camouflaged instance segmentation. To this end, we first annotate the available CAMO dataset at the instance level. We also embed the data augmentation in order to increase the number of training samples. Then, we train different state-of-the-art instance segmentation on the CAMO-instance data. Last but not least, we develop an interactive user interface which demonstrates the performance of different state-of-the-art instance segmentation methods on the task of camouflaged instance segmentation. The users are able to compare the results of different methods on the given input images. Our work is expected to push the envelope of the camouflage analysis problem.

Publisher

Association for the Advancement of Artificial Intelligence

Keywords

Camouflaged Instance Segmentation, Object Segmentation, Instance Segmentation

Sponsoring Agency

This research is in part granted by National Science Foundation (NSF) under Grant No. 2025234, University of Dayton SEED Grant, JSPS KAKENHI Grant Number 20K23355, and Vingroup Innovation Foundation (VINIF) in project code VINIF.2019.DA19

eCommons Citation

Le, Trung-Nghia; Nguyen, Vuong; Le, Cong; Nguyen, Tan-Cong; Tran, Minh-Triet; and Nguyen, Tam Van, "CamouFinder: Finding Camouflaged Instances in Images" (2021). Computer Science Faculty Publications. 236.
https://ecommons.udayton.edu/cps_fac_pub/236