Current anomaly detection paradigms face inherent limitations in simultaneously addressing structural anomalies (\eg, geometric distortions) and logical anomalies (\eg, semantic inconsistencies), due to conflicting feature representation requirements between these two anomaly categories. We propose UniAD, a novel dual-branch teacher-student framework that achieves unified anomaly detection through synergistic integration of complementary expertise from heterogeneous vision models without requirements of extra manual annotations. In particular, our framework integrates two frozen expert models as teachers: (1) a structural teacher specializing in geometric-sensitive patterns, and (2) a logical teacher focusing on semantic-aware representations via component relationship modeling. To resolve feature conflicts while preserving complementary information, the student network is equipped with one shared backbone and two independent branches. One branch employs multi-scale feature alignment with the structural teacher while another branch establishing semantic correspondence with the logical teacher through component-aware attention mechanisms. Furthermore, we introduce the text-guided semantic enhancement module as a kind of logical guidance to facilitate the anomaly indicator. Extensive experiments on the challenging MVTec LOCO benchmark validate that the scalability of our model to localize both geometric distortions and semantic inconsistencies. The proposed method outperforms existing single-purpose detectors, yielding 93.7% AUROC for logical anomalies and 93.2% AUROC for structural anomalies.

Social trust relationship prediction targets using attributes to quantify the interrelationships in trust between users. Most of the existing algorithms do not consider the heterogeneity and semantics of information included in online social networks, leading to low adaptability in capturing user preferences. What’s more, they only focus on directly connected nodes, and treat all the information propagation paths equally, leading to the lack of structure context information. Given the incomplete graph structure on online social networks constructed by existing algorithms, they can hardly have good performance in the trust prediction. In order to solve the above-mentioned problems, we propose a novel Attention-aware Multi-hop Trust Inference (AMTI) model which could capture different features on both nodes and paths adaptively based on the complex contexts and take multi-hop neighbors into account. Specifically, in our model, we construct a heterogeneous graph of three types of nodes: User, Interest, and Relationship as well as two different meta-paths: User-Interest-User, and User-Relative-User. Then, we adopt a two-level attention mechanism to obtain the attention value on both the node level and path level. To incorporate the multi-hop neighbors’ information, we develop a 2-hop attention diffusion to aggregate the information from the indirectly connected nodes. The experimental results on real-world datasets have demonstrated that AMTI outperforms the state-of-the-art methods in terms of the accuracy of social trust prediction.