AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion

TL;DR

AnomalyXFusion introduces a multi-modal diffusion framework that significantly improves the synthesis of logical anomalies by integrating image, text, and mask data, supported by a new annotated dataset.

Contribution

The paper presents a novel multi-modal anomaly synthesis framework with modules for modality fusion and controlled diffusion, and introduces the MVTec Caption dataset for enhanced anomaly representation.

Findings

Enhanced fidelity and diversity in logical anomaly synthesis

Effective multi-modal feature integration via X-embedding

Superior performance over existing methods in anomaly generation

Abstract

Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as input, which limits the fidelity of synthesized abnormal samples. Because texture information is insufficient to correctly depict the pattern of anomalies, especially for logical anomalies. To surmount this obstacle, we present the AnomalyXFusion framework, designed to harness multi-modality information to enhance the quality of synthesized abnormal samples. The AnomalyXFusion framework comprises two distinct yet synergistic modules: the Multi-modal In-Fusion (MIF) module and the Dynamic Dif-Fusion (DDF) module. The MIF module refines modality alignment by aggregating and integrating various modality features into a unified embedding space, termed X-embedding, which includes image, text, and mask features. Concurrently, the DDF module facilitates controlled generation through an adaptive adjustment of X-embedding conditioned on the diffusion steps. In addition, to reveal the multi-modality representational power of AnomalyXFusion, we propose a new dataset, called MVTec Caption. More precisely, MVTec Caption extends 2.2k accurate image-mask-text annotations for the MVTec AD and LOCO datasets. Comprehensive evaluations demonstrate the effectiveness of AnomalyXFusion, especially regarding the fidelity and diversity for logical anomalies. Project page: http:github.com/hujiecpp/MVTec-Caption