SOD-diffusion: Salient Object Detection via Diffusion-Based Image Generators
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Salient Object Detection (SOD) is a challenging task that aims to precisely identify and segment the salient objects. However, existing SOD methods still face challenges in making explicit predictions near the edges and often lack end-to-end training capabilities. To alleviate these problems, we propose SOD-diffusion, a novel framework that formulates salient object detection as a denoising diffusion process from noisy masks to object masks. Specifically, object masks diffuse from ground-truth masks to random distribution in latent space, and the model learns to reverse this noising process to reconstruct object masks. To enhance the denoising learning process, we design an attention feature interaction module (AFIM) and a specific fine-tuning protocol to integrate conditional semantic features from the input image with diffusion noise embedding. Extensive experiments on five widely used SOD benchmark datasets demonstrate that our proposed SOD-diffusion achieves favorable performance compared to previous well-established methods. Furthermore, leveraging the outstanding generalization capability of SOD-diffusion, we applied it to publicly available images, generating high-quality masks that serve as an additional SOD benchmark testset.
Description
CCS Concepts: Computing methodologies → Interest point and salient region detections
@article{10.1111:cgf.15251,
journal = {Computer Graphics Forum},
title = {{SOD-diffusion: Salient Object Detection via Diffusion-Based Image Generators}},
author = {Zhang, Shuo and Huang, Jiaming and Chen, Shizhe and Wu, Yan and Hu, Tao and Liu, Jing},
year = {2024},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.15251}
}