There have been significant advancements in anomaly detection in an unsupervised manner, where only normal images are available for training. Several recent methods aim to detect anomalies based on a memory, comparing the input and the directly stored normal features (or trained features with normal images). However, such memory-based approaches operate on a discrete feature space implemented by the nearest neighbor or attention mechanism, suffering from poor generalization or an identity shortcut issue outputting the same as input, respectively. Furthermore, the majority of existing methods are designed to detect single-class anomalies, resulting in unsatisfactory performance when presented with multiple classes of objects. To tackle all of the above challenges, we propose GRAD, a novel anomaly detection method for representing normal features within a "continuous" feature space, enabled by transforming spatial features into coordinates and mapping them to continuous grids. Furthermore, we carefully design the grids tailored for anomaly detection, representing both local and global normal features and fusing them effectively. Our extensive experiments demonstrate that GRAD successfully generalizes the normal features and mitigates the identity shortcut, furthermore, GRAD effectively handles diverse classes in a single model thanks to the high-granularity global representation. In an evaluation using the MVTec AD dataset, GRAD significantly outperforms the previous state-of-the-art method by reducing 65.0\% of the error for multi-class unified anomaly detection. The project page is available at https://tae-mo.github.io/grad/.

翻译：无监督异常检测近期取得了显著进展，此类方法仅需正常图像进行训练。部分新近方法尝试基于记忆进行异常检测，通过比较输入特征与直接存储的正常特征（或基于正常图像训练的特征）。然而，这类基于记忆的方法在由最近邻或注意力机制实现的离散特征空间中运作，前者存在泛化能力不足的问题，后者则面临输出与输入完全一致的恒等捷径困境。此外，现有方法大多针对单类异常设计，在处理多类物体时表现欠佳。为应对上述挑战，我们提出GRAD这一新型异常检测方法，通过将空间特征转换为坐标并映射至连续网格，实现在"连续"特征空间中表征正常特征。我们还针对异常检测任务精心设计了专用网格结构，可同时表征局部与全局正常特征并实现高效融合。大量实验表明，GRAD能成功泛化正常特征并有效缓解恒等捷径问题，更因其高细粒度全局表征能力，可在单一模型中妥善处理多类别异常。在MVTec AD数据集上的评估显示，GRAD将多类统一异常检测的错误率降低了65.0%，显著超越此前最优方法。项目页面详见https://tae-mo.github.io/grad/。