Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lyu, Pengfei, Yu, Xiaosheng, Yeung, Pak-Hei, Wu, Chengdong, Rajapakse, Jagath C.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914141597335552
author Lyu, Pengfei
Yu, Xiaosheng
Yeung, Pak-Hei
Wu, Chengdong
Rajapakse, Jagath C.
author_facet Lyu, Pengfei
Yu, Xiaosheng
Yeung, Pak-Hei
Wu, Chengdong
Rajapakse, Jagath C.
contents The rapid development of deep learning has significantly improved salient object detection (SOD) combining both RGB and thermal (RGB-T) images. However, existing Transformer-based RGB-T SOD models with quadratic complexity are memory-intensive, limiting their application in high-resolution bimodal feature fusion. To overcome this limitation, we propose a purely Fourier Transform-based model, namely Deep Fourier-embedded Network (FreqSal), for accurate RGB-T SOD. Specifically, we leverage the efficiency of Fast Fourier Transform with linear complexity to design three key components: (1) To fuse RGB and thermal modalities, we propose Modal-coordinated Perception Attention, which aligns and enhances bimodal Fourier representation in multiple dimensions; (2) To clarify object edges and suppress noise, we design Frequency-decomposed Edge-aware Block, which deeply decomposes and filters Fourier components of low-level features; (3) To accurately decode features, we propose Fourier Residual Channel Attention Block, which prioritizes high-frequency information while aligning channel-wise global relationships. Additionally, even when converged, existing deep learning-based SOD models' predictions still exhibit frequency gaps relative to ground-truth. To address this problem, we propose Co-focus Frequency Loss, which dynamically weights hard frequencies during edge frequency reconstruction by cross-referencing bimodal edge information in the Fourier domain. Extensive experiments on ten bimodal SOD benchmark datasets demonstrate that FreqSal outperforms twenty-nine existing state-of-the-art bimodal SOD models. Comprehensive ablation studies further validate the value and effectiveness of our newly proposed components. The code is available at https://github.com/JoshuaLPF/FreqSal.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18409
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection
Lyu, Pengfei
Yu, Xiaosheng
Yeung, Pak-Hei
Wu, Chengdong
Rajapakse, Jagath C.
Computer Vision and Pattern Recognition
The rapid development of deep learning has significantly improved salient object detection (SOD) combining both RGB and thermal (RGB-T) images. However, existing Transformer-based RGB-T SOD models with quadratic complexity are memory-intensive, limiting their application in high-resolution bimodal feature fusion. To overcome this limitation, we propose a purely Fourier Transform-based model, namely Deep Fourier-embedded Network (FreqSal), for accurate RGB-T SOD. Specifically, we leverage the efficiency of Fast Fourier Transform with linear complexity to design three key components: (1) To fuse RGB and thermal modalities, we propose Modal-coordinated Perception Attention, which aligns and enhances bimodal Fourier representation in multiple dimensions; (2) To clarify object edges and suppress noise, we design Frequency-decomposed Edge-aware Block, which deeply decomposes and filters Fourier components of low-level features; (3) To accurately decode features, we propose Fourier Residual Channel Attention Block, which prioritizes high-frequency information while aligning channel-wise global relationships. Additionally, even when converged, existing deep learning-based SOD models' predictions still exhibit frequency gaps relative to ground-truth. To address this problem, we propose Co-focus Frequency Loss, which dynamically weights hard frequencies during edge frequency reconstruction by cross-referencing bimodal edge information in the Fourier domain. Extensive experiments on ten bimodal SOD benchmark datasets demonstrate that FreqSal outperforms twenty-nine existing state-of-the-art bimodal SOD models. Comprehensive ablation studies further validate the value and effectiveness of our newly proposed components. The code is available at https://github.com/JoshuaLPF/FreqSal.
title Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.18409