论文标题
斑点差异自我监督的预训练用于异常检测和分割
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
论文作者
论文摘要
视觉异常检测通常用于工业质量检查。在本文中，我们提出了一个新的数据集以及一种新的自我监督学习方法，用于ImageNet预训练，以改善1级和2级和2级5/10/高光训练设置的异常检测和细分。我们发布了视觉异常（Visa）数据集，该数据集由10,821个高分辨率颜色图像（9,621个正常和1,200个异常样品）组成，这些图像涵盖了3个域中的12个对象，使其成为迄今为止最大的工业异常检测数据集。提供了图像和像素级标签。我们还提出了一个新的自我监督框架 - 斑点差异（SPD），该框架可以正规化对比度的自我监督的预训练，例如SIMSSIAM，MOCO和SIMCLR，以更适合异常检测任务。我们在Visa和MVTEC-AD数据集上进行的实验表明，SPD始终改善这些对比的训练前基线，甚至是受监督的预训练。例如，SPD在Precision-Recall曲线（AU-PR）下改善了SIMSIAM比SIMSIAM的分段和6.8％的区域，并分别监督了2级高射击状态的预训练。我们通过http://github.com/amazon-research/spot-diff开放项目。
Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2-class 5/10/high-shot training setups. We release the Visual Anomaly (VisA) Dataset consisting of 10,821 high-resolution color images (9,621 normal and 1,200 anomalous samples) covering 12 objects in 3 domains, making it the largest industrial anomaly detection dataset to date. Both image and pixel-level labels are provided. We also propose a new self-supervised framework - SPot-the-difference (SPD) - which can regularize contrastive self-supervised pre-training, such as SimSiam, MoCo and SimCLR, to be more suitable for anomaly detection tasks. Our experiments on VisA and MVTec-AD dataset show that SPD consistently improves these contrastive pre-training baselines and even the supervised pre-training. For example, SPD improves Area Under the Precision-Recall curve (AU-PR) for anomaly segmentation by 5.9% and 6.8% over SimSiam and supervised pre-training respectively in the 2-class high-shot regime. We open-source the project at http://github.com/amazon-research/spot-diff .
