Multi-Image Visual Question Answering for Unsupervised Anomaly Detection

arXiv:2404.07622v1 Announce Type: new
Abstract: Unsupervised anomaly detection enables the identification of potential pathological areas by juxtaposing original images with their pseudo-healthy reconstructions generated by models trained exclusively on normal images. However, the clinical interpretation of resultant anomaly maps presents a challenge due to a lack of detailed, understandable explanations. Recent advancements in language models have shown the capability of mimicking human-like understanding and providing detailed descriptions. This raises an interesting question: \textit{How can language models be employed to make …

abstract anomaly anomaly detection arxiv challenge clinical cs.cl cs.cv detection generated however identification image images interpretation maps normal question question answering type unsupervised visual