The Art of Camouflage: Few-shot Learning for Animal Detection and Segmentation

作     者：Nguyen, Thanh-Danh Vu, Anh-Khoa Nguyen Nguyen, Nhat-Duy Nguyen, Vinh-Tiep Ngo, Thanh Duc Do, Thanh-Toan Tran, Minh-Triet Nguyen, Tam V. 

作者机构：Laboratory of Multimedia Communications University of Information Technology Ho Chi Minh City Viet Nam Faculty of Computer Science University of Information Technology Ho Chi Minh City Viet Nam Faculty of Information Technology University of Science Ho Chi Minh City Viet Nam John von Neumann Institute VNU-HCM Viet Nam Vietnam National University Ho Chi Minh City Viet Nam Faculty of Information Technology Monash University ClaytonVIC3800 Australia Department of Computer Science University of Dayton DaytonOH45469 United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Zero shot learning 

摘      要：Camouflaged object detection and segmentation is a new and challenging research topic in computer vision. There is a serious issue of lacking data on concealed objects such as camouflaged animals in natural scenes. In this paper, we address the problem of few-shot learning for camouflaged object detection and segmentation. To this end, we first collect a new dataset, CAMO-FS, for the benchmark. As camouflaged instances are challenging to recognize due to their similarity compared to the surroundings, we guide our models to obtain camouflaged features that highly distinguish the instances from the background. In this work, we propose FS-CDIS, a framework to efficiently detect and segment camouflaged instances via two loss functions contributing to the training process. Firstly, the instance triplet loss with the characteristic of differentiating the anchor, which is the mean of all camouflaged foreground points, and the background points are employed to work at the instance level. Secondly, to consolidate the generalization at the class level, we present instance memory storage with the scope of storing camouflaged features of the same category, allowing the model to capture further class-level information during the learning process. The extensive experiments demonstrated that our proposed method achieves state-of-the-art performance on the newly collected dataset. Code is available at https://***/danhntd/FS-CDIS. © 2023, CC BY-NC-ND.