Diffusion Model for Camouflaged Object Detection

TL;DR

This paper introduces diffCOD, a diffusion model-based framework for camouflaged object detection that leverages a denoising process guided by image priors and an attention module, achieving superior segmentation performance.

Contribution

The paper proposes a novel diffusion-based approach for camouflaged object detection, integrating image priors and an injection attention module for improved denoising and segmentation accuracy.

Findings

Outperforms 11 state-of-the-art methods on four COD benchmarks.

Effectively captures detailed textures of camouflaged objects.

Demonstrates the effectiveness of diffusion models in segmentation tasks.

Abstract

Camouflaged object detection is a challenging task that aims to identify objects that are highly similar to their background. Due to the powerful noise-to-image denoising capability of denoising diffusion models, in this paper, we propose a diffusion-based framework for camouflaged object detection, termed diffCOD, a new framework that considers the camouflaged object segmentation task as a denoising diffusion process from noisy masks to object masks. Specifically, the object mask diffuses from the ground-truth masks to a random distribution, and the designed model learns to reverse this noising process. To strengthen the denoising learning, the input image prior is encoded and integrated into the denoising diffusion model to guide the diffusion process. Furthermore, we design an injection attention module (IAM) to interact conditional semantic features extracted from the image with the diffusion noise embedding via the cross-attention mechanism to enhance denoising learning. Extensive experiments on four widely used COD benchmark datasets demonstrate that the proposed method achieves favorable performance compared to the existing 11 state-of-the-art methods, especially in the detailed texture segmentation of camouflaged objects. Our code will be made publicly available at: https://github.com/ZNan-Chen/diffCOD.