{"type":"ScholarlyArticle","title":"HyperTrans: Efficient Hypergraph-Driven Cross-Domain Pattern Transfer in Image Anomaly Detection","authors":[{"name":"Tengyu Zhang","slug":"tengyu-zhang","given":"Tengyu","family":"Zhang","affiliation":""},{"name":"Deyu Zeng","slug":"deyu-zeng","given":"Deyu","family":"Zeng","affiliation":""},{"name":"Baoqiang Li","slug":"baoqiang-li","given":"Baoqiang","family":"Li","affiliation":""},{"name":"Wei Wang","slug":"wei-wang","given":"Wei","family":"Wang","affiliation":""},{"name":"Wei Liu","slug":"wei-liu","given":"Wei","family":"Liu","affiliation":""},{"name":"Zongze Wu","slug":"zongze-wu","given":"Zongze","family":"Wu","affiliation":""}],"abstract":"Anomaly detection plays a pivotal role in industrial quality assurance processes, with cross-domain problems, exemplified by the model upgrade from RGB to 3D, being prevalent in real-world scenarios yet remaining systematically underexplored. To address the severe challenges posed by the extreme lack of datasets in target domain, we retain the knowledge from source models and explore a novel solution for anomaly detection through cross-domain learning, introducing HyperTrans. Targeting few-shot scenarios, HyperTrans centers around hypergraphs to model the relationship of the limited patch features and employs a perturbation-rectification-scoring architecture. The domain perturbation module injects and adapts channel-level statistical perturbations, mitigating style shifts during domain transfer. Subsequently, a residual hypergraph restoration module utilizes a cross-domain hypergraph to capture higher-order correlations in patches and align them across domains. Ultimately, with feature patterns exhibiting reduced domain shifts, an inter-domain scoring module aggregates similarity information between patches and normal patterns within the multi-domain subhypergraphs to make an integrated decision, generating multi-level anomaly predictions. Extensive experiments demonstrate that HyperTrans offers significant advantages in anomaly classification and anomaly segmentation tasks, outperforming state-of-the-art non-cross-domain methods in image-wise ROCAUC by 13%, 12%, and 15% in 1-shot, 2-shot, and 5-shot settings on MVTec3D AD.","doi":"10.24963/ijcai.2025/267","url":"https://ijcai.org/proceedings/2025/267","pdf":"https://ijcai.org/proceedings/2025/0267.pdf","markdown":"https://ijcai.org/proceedings/2025/267.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/267","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":267,"pages":{"first":2395,"last":2403},"keywords":["Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: CV: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}