Constrained Adaptive Projection with Pretrained Features for Anomaly Detection

2021-12-05 · Xingtai Gui, Di wu, Yang Chang, Shicai Fan

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). Combined with pretrained features, a simple linear projection head applied on a specific input and its k most similar pretrained normal representations is designed for feature adaptation, and a reformed self-attention is leveraged to mine the inner-relationship among one-class semantic features. A loss function is proposed to avoid potential pattern collapse. Concretely, it considers the similarity between a specific data and its corresponding adaptive normal representation, and incorporates a constraint term slightly aligning pretrained and adaptive spaces. Our method achieves state-ofthe-art anomaly detection performance on semantic anomaly detection and sensory anomaly detection benchmarks including 96.5% AUROC on CIFAR- 100 dataset, 97.0% AUROC on CIFAR-10 dataset and 89.9% AUROC on MvTec dataset.

📄 PDF Abstract BibTeX arXiv:2112.02597

Code (1)

tabguigui/cap 공식 구현 pytorch

Tasks

Anomaly Detection

GFM4GA: Graph Foundation Model for Group Anomaly Detection

2026-01-15 · Jiujiu Chen, Weijun Zeng, Shaofeng Hu, Sihong Xie 외 arxiv

Group anomaly detection is crucial in many network applications, but faces challenges due to diverse anomaly patterns. Motivated by the success of large language models (LLMs) in natural language processing, graph founda…

Contrastive Learning Few-Shot Learning Anomaly Detection

NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning

2025-07-10 · Tianwei Mu, Feiyu Duan, Bo Zhou, Dan Xue 외 arxiv

This paper presents a novel few-shot cross-domain anomaly detection framework, Nexus Vision Transformer for Anomaly Detection (NexViTAD), based on vision foundation models, which effectively addresses domain-shift challe…

Multi-Task Learning Anomaly Detection

Distributed and Rate-Adaptive Feature Compression

2024-04-02 · Aditya Deshmukh, Venugopal V. Veeravalli, Gunjan Verma

We study the problem of distributed and rate-adaptive feature compression for linear regression. A set of distributed sensors collect disjoint features of regressor data. A fusion center is assumed to contain a pretraine…

Feature Compression regression

ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining

2025-11-07 · Xincheng Yao, Yan Luo, Zefeng Qian, Chongyang Zhang arxiv

The current mainstream and state-of-the-art anomaly detection (AD) methods are substantially established on pretrained feature networks yielded by ImageNet pretraining. However, regardless of supervised or self-supervise…

Representation Learning Anomaly Detection

PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

2020-10-12 · CVPR 2021 1 · Tal Reiss, Niv Cohen, Liron Bergman, Yedid Hoshen

Anomaly detection methods require high-quality features. In recent years, the anomaly detection community has attempted to obtain better features using advances in deep self-supervised feature learning. Surprisingly, a v…

Anomaly Detection Anomaly Segmentation Continual Learning Multi-class Classification+2