Frequency Perception Network for Camouflaged Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cong, Runmin, Sun, Mengyao, Zhang, Sanyi, Zhou, Xiaofei, Zhang, Wei, Zhao, Yao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912147391381504
author Cong, Runmin
Sun, Mengyao
Zhang, Sanyi
Zhou, Xiaofei
Zhang, Wei
Zhao, Yao
author_facet Cong, Runmin
Sun, Mengyao
Zhang, Sanyi
Zhou, Xiaofei
Zhang, Wei
Zhao, Yao
contents Camouflaged object detection (COD) aims to accurately detect objects hidden in the surrounding environment. However, the existing COD methods mainly locate camouflaged objects in the RGB domain, their performance has not been fully exploited in many challenging scenarios. Considering that the features of the camouflaged object and the background are more discriminative in the frequency domain, we propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain. Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage. With the multi-level features extracted by the backbone, we design a flexible frequency perception module based on octave convolution for coarse positioning. Then, we design the correction fusion module to step-by-step integrate the high-level features through the prior-guided correction and cross-layer feature channel association, and finally combine them with the shallow features to achieve the detailed correction of the camouflaged objects. Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets both qualitatively and quantitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2308_08924
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Frequency Perception Network for Camouflaged Object Detection
Cong, Runmin
Sun, Mengyao
Zhang, Sanyi
Zhou, Xiaofei
Zhang, Wei
Zhao, Yao
Computer Vision and Pattern Recognition
Camouflaged object detection (COD) aims to accurately detect objects hidden in the surrounding environment. However, the existing COD methods mainly locate camouflaged objects in the RGB domain, their performance has not been fully exploited in many challenging scenarios. Considering that the features of the camouflaged object and the background are more discriminative in the frequency domain, we propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain. Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage. With the multi-level features extracted by the backbone, we design a flexible frequency perception module based on octave convolution for coarse positioning. Then, we design the correction fusion module to step-by-step integrate the high-level features through the prior-guided correction and cross-layer feature channel association, and finally combine them with the shallow features to achieve the detailed correction of the camouflaged objects. Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets both qualitatively and quantitatively.
title Frequency Perception Network for Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.08924