Abstract
Weakly-supervised diffusion models (DM) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need for pixel-level labels in training, offering a more cost-effective alternative to supervised methods. However, existing methods are not fully weakly-supervised because they heavily rely on costly pixel-level labels for hyperparameter tuning in inference. To tackle this challenge, we introduce Anomaly Segmentation with Forward Process of Diffusion Models (AnoFPDM), a fully weakly-supervised framework that operates without the need for pixel-level labels. Leveraging the unguided forward process as a reference, we identify suitable hyperparameters, i.e., noise scale and threshold, for each input image. We aggregate anomaly maps from each step in the forward process, enhancing the signal strength of anomalous regions. Remarkably, our proposed method outperforms recent state-of-the-art weakly-supervised approaches, even without utilizing pixel-level labels.
Abstract (translated)
在异常分割中,利用图像级标签弱监督扩散模型(DM)吸引了广泛的关注,因为它们与无监督方法的优越性能。它消除了在训练过程中需要像素级标签的需求,为监督方法提供了一种更经济有效的替代方案。然而,现有的方法并不是完全弱监督的,因为它们在推理过程中严重依赖昂贵的像素级标签进行超参数调整。为了解决这个挑战,我们引入了异常分割扩散模型前向过程(AnoFPDM),一种完全弱监督的框架,不需要像素级标签。利用无引导的前向过程作为参考,我们确定每个输入图像的合适超参数,即噪声比例和阈值。我们从前向过程的每个步骤中累积异常图,增强异常区域的信号强度。值得注意的是,与最先进的弱监督方法相比,我们的方法甚至在没有使用像素级标签的情况下表现出色。
URL
https://arxiv.org/abs/2404.15683