Effective multi-view subspace learning is crucial for enhancing classification performance on multi-view data. In this paper, we propose CMvLSCN, a novel end-to-end framework addressing multi-view classification at view, sample, and subspace levels. The key innovations are: Strengthening inter-view consistency within categories while weakening inter-view similarity across categories; Learning a unified latent subspace representation through the view fusion; and Imposing low-rank latent self-representation and hierarchical contrastive constraints to better classify multi-view data. CMvLSCN employs contrastive learning to optimize Kullback-Leibler divergence among views, imposes low-rank structure on the latent subspace, and introduces sample-level contrastive constraints. This approach captures underlying data relationships and enhances subspace representation discriminability. Experiments demonstrate superior performance, especially with limited training data. Code and datasets are available on GitHub.

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.

Multiview data classification remains a challenging problem in machine learning, particularly in effectively integrating and representing data from different views. This article introduces contrastive multiview low-rank latent subspace self-representation and classification network (CMvLSCN), a novel end-to-end multiview discriminant learning framework that addresses classification from view, sample, and subspace levels. CMvLSCN employs contrastive learning to enhance interview consistency within categories while differentiating between categories. It imposes a low-rank latent self-representation structure on the unified subspace, capturing intrinsic data relationships. Additionally, sample-level contrastive constraints in the latent space further boost the representation’s discriminative power. Extensive experiments demonstrate CMvLSCN’s superior performance across various multiview classification tasks, notably maintaining robustness even with limited training data. Our code and datasets are publicly available on https://github.com/DeyuTsang/CMvLSCN

Abstract Manual or conventional image processing algorithms are commonly used to detect surface problems on mobile phone screens. However, inefficiency and inflexibility are disadvantages. Although the semantic segmentation method has high adaptability and accuracy, it also has a low defect detection efficiency due to its excessive parameters. In order to increase defect detection efficiency, a novel efficient encoder–decoder architecture termed MB encoder–decoder architecture based on MBConv blocks, and that it reduces the number of parameters used in semantic segmentation methods i presented. In addition, by applying the MB encoder–decoder design to the U‐Net, the efficient U‐Net (EU‐Net) is proposed. It confirms the MB encoder–decoder architecture's superiority. Then, EU‐Net to mobile phone surface defect detection in real industrial scenarios. Experimental results on a dataset show the superiority of the proposed algorithm and it can meet the real‐time requirement of industrial production.

Rank minimization is widely used to extract low-dimensional subspaces. As a convex relaxation of the rank minimization, the problem of nuclear norm minimization has been attracting widespread attention. However, the standard nuclear norm minimization usually results in overcompression of data in all subspaces and eliminates the discrimination information between different categories of data. To overcome these drawbacks, in this article, we introduce the label information into the nuclear norm minimization problem and propose a labeled-robust principal component analysis (L-RPCA) to realize nuclear norm minimization on multisubspace data. Compared with the standard nuclear norm minimization, our method can effectively utilize the discriminant information in multisubspace rank minimization and avoid excessive elimination of local information and multisubspace characteristics of the data. Then, an effective labeled-robust regression (L-RR) method is proposed to simultaneously recover the data and labels of the observed data. Experiments on real datasets show that our proposed methods are superior to other state-of-the-art methods.