Surface defect segmentation in metallic materials presents significant challenges due to irregular defect shapes, extreme scale variations ranging from small blowholes to large uneven regions, and low contrast with complex background textures. While Convolutional Neural Networks excel at local feature extraction, their limited receptive fields hinder effective global context modeling. Conversely, Vision Transformers capture long-range dependencies but struggle with fine-grained boundary details critical for accurate defect localization. To address these limitations, we propose FocusNet, a novel architecture integrating multi-scale feature refinement, hybrid attention mechanisms, and progress... More >

Salient object detection aims to identify and segment the most visually prominent objects in images. Despite significant advances in deep learning, existing methods struggle to balance global context modeling, boundary preservation, and multi-scale feature integration. To address these limitations, we propose MAFNet (Multi-level Attention Fusion Network), a novel attention-driven framework that leverages specialized attention mechanisms tailored to different semantic levels. Our approach employs a Tokens-to-Token (T2T) Transformer backbone for hierarchical feature extraction, capturing both local structural details and global contextual relationships. The core contribution lies in a comprehe... More >