Frequency-Spatial Entanglement Learning for Camouflaged Object Detection

TL;DR

This paper introduces Frequency-Spatial Entanglement Learning (FSEL), a novel method combining frequency and spatial domain features to improve camouflaged object detection, outperforming existing approaches.

Contribution

The paper proposes a new FSEL approach with Entanglement Transformer Blocks and dual-domain feature integration for better camouflaged object detection.

Findings

FSEL outperforms 21 state-of-the-art methods.

Extensive experiments validate the effectiveness of the approach.

The method achieves superior results on three benchmark datasets.

Abstract

Camouflaged object detection has attracted a lot of attention in computer vision. The main challenge lies in the high degree of similarity between camouflaged objects and their surroundings in the spatial domain, making identification difficult. Existing methods attempt to reduce the impact of pixel similarity by maximizing the distinguishing ability of spatial features with complicated design, but often ignore the sensitivity and locality of features in the spatial domain, leading to sub-optimal results. In this paper, we propose a new approach to address this issue by jointly exploring the representation in the frequency and spatial domains, introducing the Frequency-Spatial Entanglement Learning (FSEL) method. This method consists of a series of well-designed Entanglement Transformer Blocks (ETB) for representation learning, a Joint Domain Perception Module for semantic enhancement, and a Dual-domain Reverse Parser for feature integration in the frequency and spatial domains. Specifically, the ETB utilizes frequency self-attention to effectively characterize the relationship between different frequency bands, while the entanglement feed-forward network facilitates information interaction between features of different domains through entanglement learning. Our extensive experiments demonstrate the superiority of our FSEL over 21 state-of-the-art methods, through comprehensive quantitative and qualitative comparisons in three widely-used datasets. The source code is available at: https://github.com/CSYSI/FSEL.