Anomaly detection (AD) is essential for industrial inspection and medical diagnosis, yet existing methods typically rely on ``comparing'' test images to normal references from a training set. However, variations in appearance and positioning often complicate the alignment of these references with the test image, limiting detection accuracy. We observe that most anomalies manifest as local variations, meaning that even within anomalous images, valuable normal information remains. We argue that this information is useful and may be more aligned with the anomalies since both the anomalies and the normal information originate from the same image. Therefore, rather than relying on external normality from the training set, we propose INP-Former, a novel method that extracts Intrinsic Normal Prototypes (INPs) directly from the test image. Specifically, we introduce the INP Extractor, which linearly combines normal tokens to represent INPs. We further propose an INP Coherence Loss to ensure INPs can faithfully represent normality for the testing image. These INPs then guide the INP-guided Decoder to reconstruct only normal tokens, with reconstruction errors serving as anomaly scores. Additionally, we propose a Soft Mining Loss to prioritize hard-to-optimize samples during training. INP-Former achieves state-of-the-art performance in single-class, multi-class, and few-shot AD tasks across MVTec-AD, VisA, and Real-IAD, positioning it as a versatile and universal solution for AD. Remarkably, INP-Former also demonstrates some zero-shot AD capability. Furthermore, we propose a soft version of the INP Coherence Loss and enhance INP-Former by incorporating residual learning, leading to the development of INP-Former++. The proposed method significantly improves detection performance across single-class, multi-class, semi-supervised, few-shot, and zero-shot settings.
View on arXiv@article{luo2025_2506.03660,
title={ INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning },
author={ Wei Luo and Haiming Yao and Yunkang Cao and Qiyu Chen and Ang Gao and Weiming Shen and Wenyong Yu },
journal={arXiv preprint arXiv:2506.03660},
year={ 2025 }
}