SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection

Zongxiang Hu; Zhaosheng Zhang

SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection

Computer Vision and Pattern Recognition 2024-11-20 v4

Authors: Zongxiang Hu , Zhaosheng Zhang

Abstract

Visual anomaly detection is essential in industrial manufacturing, yet traditional methods often rely heavily on extensive normal datasets and task-specific models, limiting their scalability. Recent advancements in large-scale vision-language models have significantly enhanced zero- and few-shot anomaly detection. However, these approaches may not fully leverage hierarchical features, potentially overlooking nuanced details crucial for accurate detection. To address this, we introduce a novel window self-attention mechanism based on the CLIP model, augmented with learnable prompts to process multi-level features within a Soldier-Officer Window Self-Attention (SOWA) framework. Our method has been rigorously evaluated on five benchmark datasets, achieving superior performance by leading in 18 out of 20 metrics, setting a new standard against existing state-of-the-art techniques.

Keywords

anomaly detection visual-language models window self-attention CLIP few-shot learning frozen models

Cite

@article{arxiv.2407.03634,
  title  = {SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection},
  author = {Zongxiang Hu and Zhaosheng Zhang},
  journal= {arXiv preprint arXiv:2407.03634},
  year   = {2024}
}

Comments

8 pages, 9 figures, conference

SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection

Abstract

Keywords

Cite

Comments

Related papers