CORTEXA
← Browse
arxivcs.CV2026-07-14

A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition

Shrey Patel

Automated visual inspection of steel surface defects is a recurring quality control task in which labeled defect data is scarce and costly to obtain, while unlabeled surface images are abundant, which motivates self supervised methods that learn useful representations without class labels. A Transformer based Masked Autoencoder is used here to learn representations of steel surface defects for unsupervised grouping. During pretraining, 75% of the input image patches are randomly masked, and a lightweight decoder reconstructs the masked regions from the visible 25%. The encoder is trained jointly with an auxiliary defect localization objective, used only as a training signal and not evaluated as a detector. The decoder reaches a structural similarity score of 0.92 and a mean squared error of 0.47. Features from the pretrained encoder are then clustered using UMAP for dimensionality reduction and Agglomerative clustering, reaching a Hungarian matched accuracy of 91.3% against the six known defect categories.

View free PDFSource page

Related papers

arxivcs.CV2026-07-23

SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation

Zhongming Liu, Bingbing Jiang, Guangxin Wan, Xiang Zou

Steel surface defect segmentation is critical for industrial quality inspection, yet existing methods struggle with elongated, anisotropic defects such as cracks and scratches due to the isotropic receptive fields of standard convolutions and rigid sampling grids that cannot adap…

View free PDFSource page
arxivcs.CVcs.AI2026-06-30

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

Xu Yan, Huiqun Wang, Chen Wang, Lei Ren, Di Huang

Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across downstream tasks. Unlike its 2D counterpart, 3D masked autoencoding directly reconstructs spatial coordinates, making it inherently su…

View free PDFSource page
arxivcs.CVcs.AI2026-07-16

Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach

Elena Ryumina, Maxim Markitantov, Alexandr Axyonov, Fedor Shchetinin, Timur Abdulkadirov, Dmitry Ryumin, et al.

Automatic recognition of ambivalence and hesitancy is challenging because these states may be expressed through inconsistent linguistic, acoustic, facial, and contextual patterns, while top-performing systems often rely on computationally expensive ensembles. We present a single…

View free PDFSource page
arxivcs.CVcs.AI2026-07-03

PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition

Dana A Abdullah

The widespread adoption of facial masks, accelerated by COVID-19 and mandated in security-sensitive settings, has exposed limitations of conventional face recognition systems. Existing approaches relying on fixed cosine thresholds, non-adaptive CNNs, and purely data-driven featur…

View free PDFSource page
arxivcs.CV2026-07-08

A Generalized Deep Non-negative Matrix Factorization Approach for SAR Automatic Target Recognition

Yunhong Zhang, Changjie Cao, Zhongli Zhou, Bingli Liu, Zongjie Cao, Zongyong Cui, et al.

The deep nonnegative matrix factorization (DNMF) technique is proposed to address the low interpretability of deep learning-based methods in extracting multilayer features from synthetic aperture radar (SAR) target samples. However, existing DNMF methods employ a layer-by-layer d…

View free PDFSource page