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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: 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.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914901549645824
author 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.
author_facet 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.
contents 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://github.com/danhntd/FS-CDIS.
format Preprint
id arxiv_https___arxiv_org_abs_2304_07444
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
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.
Computer Vision and Pattern Recognition
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://github.com/danhntd/FS-CDIS.
title The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.07444