VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detection

TL;DR

VTFusion introduces a multimodal fusion network that leverages domain-specific vision-text features and a dedicated fusion module to improve few-shot anomaly detection in industrial settings.

Contribution

The paper presents a novel vision-text fusion framework with adaptive feature extractors and a specialized fusion module tailored for industrial anomaly detection.

Findings

Achieves 96.8% AUROC in 2-shot MVTec AD dataset

Attains 86.2% AUROC on VisA dataset

Reaches 93.5% AUPRO on industrial automotive parts dataset

Abstract

Few-Shot Anomaly Detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pre-trained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal interference. To bridge these gaps, this study proposes VTFusion, a vision-text multimodal fusion framework tailored for FSAD. The framework rests on two core designs. First, adaptive feature extractors for both image and text modalities are introduced to learn task-specific representations, bridging the domain gap between pre-trained models and industrial data; this is further augmented by generating diverse synthetic anomalies to enhance feature discriminability. Second, a dedicated multimodal prediction fusion module is developed, comprising a fusion block that facilitates rich cross-modal information exchange and a segmentation network that generates refined pixel-level anomaly maps under multimodal guidance. VTFusion significantly advances FSAD performance, achieving image-level AUROCs of 96.8% and 86.2% in the 2-shot scenario on the MVTec AD and VisA datasets, respectively. Furthermore, VTFusion achieves an AUPRO of 93.5% on a real-world dataset of industrial automotive plastic parts introduced in this paper, further demonstrating its practical applicability in demanding industrial scenarios.