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

2024-07-04 · Zongxiang Hu, Zhaosheng Zhang

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.

📄 PDF Abstract BibTeX arXiv:2407.03634

Code (1)

huzongxiang/sowa 공식 구현 pytorch

Tasks

Anomaly Detection

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

SOWAHA as a Cancer Suppressor Gene Influence Metabolic Reprogramming

2024-09-24 · Xiaohong Yi, Xianwen Zhang, Claire H. Zhao, Yuhui Chen 외

SOWAHA is a protein-coding gene, also known as ANKRD43. Studies have indicated that SOWAHA can serve as a prognostic biomarker in colorectal cancer and pancreatic cancer. However, there are few reports about SOWAHA in ot…

Diagnostic Prognosis

When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation

2026-07-02 · Tyler Rust, Chandra Kambhamettu arxiv

Adapting frozen vision foundation models to fine-grained segmentation now largely depends on backbone selection. Whether the backbone applies global attention to a high-resolution token set predicts whether a low-rank ad…

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

2021-03-25 · ICCV 2021 10 · Ze Liu, Yutong Lin, Yue Cao, Han Hu 외

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differen…

image-classification Image Classification Instance Segmentation Object Detection+3

What Makes for Hierarchical Vision Transformer?

2021-07-05 · Yuxin Fang, Xinggang Wang, Rui Wu, Wenyu Liu

Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance…

Instance Segmentation object-detection Object Detection Semantic Segmentation+1

HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution

2024-07-08 · Xiang Zhang, Yulun Zhang, Fisher Yu

Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computatio…

Image Super-Resolution Super-Resolution