Jingyu Liu

Victor Solomon, Piet Martens, Jingyu Liu et al.

Accurate segmentation of solar filaments in H-alpha observations is critical for determining filament chirality, a key factor in the behavior of Coronal Mass Ejections (CMEs). However, existing methods often fail to capture fine-scale filament structures, particularly barbs, due to a limited ability to model long-range dependencies and spatial detail. We propose EdgeAttNet, a segmentation architecture built on a U-Net backbone by introducing a novel, learnable edge map derived directly from the input image. This edge map is incorporated into the model by linearly transforming the attention Key and Query matrices with the edge information, thereby guiding the self-attention mechanism at the network's bottleneck to more effectively capture filament boundaries and barbs. By explicitly integrating this structural prior into the attention computations, EdgeAttNet enhances spatial sensitivity and segmentation accuracy while reducing the number of trainable parameters. Trained end-to-end, EdgeAttNet outperforms U-Net and other U-Net-based transformer baselines on the MAGFILO dataset. It achieves higher segmentation accuracy and significantly better recognition of filament barbs, with faster inference performance suitable for practical deployment.

Md Tauhidul Islam, Wu Da-Wen, Tang Qing-Qing et al.

Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular diseases. Although the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field, yet issues like limited training data, imbalance data distribution, and inadequate feature extraction persist, hindering both the segmentation performance and optimal model generalization. Addressing these critical issues, the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs, thereby improving both richer feature encoding and enhanced model generalization. A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature fusion. In response to the task-specific need for higher precision where false positives are very costly, traditional skip connections are replaced with the attention-guided feature reconstructing fusion module. Additionally, innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance, further boosting the robustness and generalization of the model. With a comprehensive suite of evaluation metrics, extensive validations on four benchmark datasets (DRIVE, CHASEDB1, STARE, and HRF) and an SLO dataset (IOSTAR), demonstrate the proposed method's superiority over both baseline and state-of-the-art models. Particularly the proposed method significantly outperforms the compared methods in cross-validation model generalization.