Camouflaged Object Detection (COD) is a challenging task in computer vision
due to the high similarity between camouflaged objects and their surroundings.
Existing COD methods primarily employ semantic segmentation, which suffers from
overconfident incorrect predictions. In this paper, we propose a new paradigm
that treats COD as a conditional mask-generation task leveraging diffusion
models. Our method, dubbed CamoDiffusion, employs the denoising process of
diffusion models to iteratively reduce the noise of the mask. Due to the
stochastic sampling process of diffusion, our model is capable of sampling
multiple possible predictions from the mask distribution, avoiding the problem
of overconfident point estimation. Moreover, we develop specialized learning
strategies that include an innovative ensemble approach for generating robust
predictions and tailored forward diffusion methods for efficient training,
specifically for the COD task. Extensive experiments on three COD datasets
attest the superior performance of our model compared to existing
state-of-the-art methods, particularly on the most challenging COD10K dataset,
where our approach achieves 0.019 in terms of MAE.

在计算机视觉中，把伪装目标检测（Camouflaged Object Detection，COD）视为基于扩散模型的条件掩蔽生成任务，提出了一种名为 CamoDiffusion 的方法，它使用扩散模型的去噪过程来迭代地减少掩蔽的噪声，其随机采样的过程使得其模型能够从掩蔽分布中采样多个可能的预测，避免了过分预测错误的问题，该文的实验表明，与现有最先进的方法相比，在三个 COD 数据集上，特别是在最具挑战性的 COD10K 数据集上，我们的方法达到了 0.019 的 MAE（平均绝对误差），表现出优越的性能。