paper-with-me

Papers

Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection

2025-03-04 · CVPR 2025 1 · Wei Luo, Yunkang Cao, Haiming Yao, Xiaotian Zhang, Jianan Lou, Yuqi Cheng, Weiming Shen, Wenyong Yu

Anomaly detection (AD) is essential for industrial inspection, 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. Code is available at:https://github.com/luow23/INP-Former.

📄 PDF Abstract BibTeX arXiv:2503.02424

Code (2)

luow23/inp-former 공식 구현 pytorch
septmars/DL pytorch

Tasks

Anomaly DetectionMulti-class Anomaly Detection

Similar Papers 제목 키워드 기반

INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning

2025-06-04 · Wei Luo, Haiming Yao, Yunkang Cao, Qiyu Chen 외

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 appea…

Anomaly DetectionMedical Diagnosis

Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection

2024-08-23 · Zhijin Dong, Hongzhi Liu, Boyuan Ren, Weimin Xiong 외

Anomaly detection is a crucial task in various domains. Most of the existing methods assume the normal sample data clusters around a single central prototype while the real data may consist of multiple categories or subg…

Anomaly DetectionContrastive LearningSupervised Anomaly DetectionWeakly-supervised Anomaly Detection

Shadow Removal from Single RGB-D Images

2014-06-01 · CVPR 2014 6 · Yao Xiao, Efstratios Tsougenis, Chi-Keung Tang

We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key a…

Intrinsic Image DecompositionShadow Removal

This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse

2026-03-09 · Junhao Jia, Jiaqi Wang, Yunyou Liu, Haodong Jing 외 arxiv

Prototype networks provide an intrinsic case based explanation mechanism, but their interpretability is often undermined by prototype collapse, where multiple prototypes degenerate to highly redundant evidence. We attrib…

Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification

2026-06-25 · Duarte Leão, Diogo Pereira Araújo, Catarina Barata, Carlos Santiago arxiv

Prototype-based neural networks aim to provide intrinsic interpretability by grounding predictions in a small set of part prototypes. However, modern vision backbones typically operate in normalized, directional embeddin…