AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning

TL;DR

AnoSeg introduces a self-supervised learning approach for precise anomaly segmentation in industrial images, utilizing synthetic data generation, pixel-wise and adversarial losses, and coordinate channels to improve accuracy.

Contribution

The paper presents a novel anomaly segmentation network that leverages self-supervised learning with synthetic anomaly data, hard augmentation, and coordinate channels for enhanced segmentation accuracy.

Findings

Outperforms state-of-the-art methods on MVTec AD dataset

Achieves superior IoU scores in anomaly segmentation

Effective in localizing defects accurately

Abstract

Anomaly segmentation, which localizes defective areas, is an important component in large-scale industrial manufacturing. However, most recent researches have focused on anomaly detection. This paper proposes a novel anomaly segmentation network (AnoSeg) that can directly generate an accurate anomaly map using self-supervised learning. For highly accurate anomaly segmentation, the proposed AnoSeg considers three novel techniques: Anomaly data generation based on hard augmentation, self-supervised learning with pixel-wise and adversarial losses, and coordinate channel concatenation. First, to generate synthetic anomaly images and reference masks for normal data, the proposed method uses hard augmentation to change the normal sample distribution. Then, the proposed AnoSeg is trained in a self-supervised learning manner from the synthetic anomaly data and normal data. Finally, the coordinate channel, which represents the pixel location information, is concatenated to an input of AnoSeg to consider the positional relationship of each pixel in the image. The estimated anomaly map can also be utilized to improve the performance of anomaly detection. Our experiments show that the proposed method outperforms the state-of-the-art anomaly detection and anomaly segmentation methods for the MVTec AD dataset. In addition, we compared the proposed method with the existing methods through the intersection over union (IoU) metric commonly used in segmentation tasks and demonstrated the superiority of our method for anomaly segmentation.