单张图像足矣：无需训练数据的零样本异常定位
A Single Image Is All You Need: Zero-Shot Anomaly Localization Without Training Data
AI总结：
针对零样本异常定位中无训练数据仅提供测试图像的问题，提出受DIP启发的SSDnet，通过基于补丁的自重建框架及感知损失等技术，在MVTec-AD和织物数据集上取得优于SOTA的性能。
摘要：
图像异常检测通常通过从训练数据集集合中学习或依赖参考样本来解决。然而，在许多现实场景中，此类训练数据可能不可用，仅提供测试图像本身。我们通过提出一种利用卷积神经网络归纳偏置的单图像异常定位方法来解决这一零样本设置，该方法受深度图像先验（Deep Image Prior, DIP）启发，名为单样本分解网络（Single Shot Decomposition Network, SSDnet）。我们的关键假设是，自然图像通常表现出统一的纹理和模式，而异常表现为与这些重复或随机模式的局部偏差。为学习深度图像先验，我们设计了基于补丁的训练框架，将输入图像直接输入网络进行自重建，而非像DIP那样将随机噪声映射到图像。为避免模型简单学习恒等映射，我们应用掩蔽、补丁洗牌和小高斯噪声。此外，我们使用基于内积相似性的感知损失来捕捉像素保真度之外的结构。我们的方法无需外部训练数据、标签或参考，在存在噪声或缺失像素时仍保持稳健。SSDnet在MVTec-AD上实现0.99的AUROC和0.60的AUPRC，在织物数据集上实现0.98的AUROC和0.67的AUPRC，优于现有最先进方法。实现代码将在https://github.com/mehrdadmoradi124/SSDnet发布。
英文摘要：
Anomaly detection in images is typically addressed by learning from collections of training data or relying on reference samples. In many real-world scenarios, however, such training data may be unavailable, and only the test image itself is provided. We address this zero-shot setting by proposing a single-image anomaly localization method that leverages the inductive bias of convolutional neural networks, inspired by Deep Image Prior (DIP). Our method is named Single Shot Decomposition Network (SSDnet). Our key assumption is that natural images often exhibit unified textures and patterns, and that anomalies manifest as localized deviations from these repetitive or stochastic patterns. To learn the deep image prior, we design a patch-based training framework where the input image is fed directly into the network for self-reconstruction, rather than mapping random noise to the image as done in DIP. To avoid the model simply learning an identity mapping, we apply masking, patch shuffling, and small Gaussian noise. In addition, we use a perceptual loss based on inner-product similarity to capture structure beyond pixel fidelity. Our approach needs no external training data, labels, or references, and remains robust in the presence of noise or missing pixels. SSDnet achieves 0.99 AUROC and 0.60 AUPRC on MVTec-AD and 0.98 AUROC and 0.67 AUPRC on the fabric dataset, outperforming state-of-the-art methods. The implementation code will be released at https://github.com/mehrdadmoradi124/SSDnet
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
