EdgeAttNet: Towards Barb-Aware Filament Segmentation
This work addresses a domain-specific problem in solar physics for researchers studying Coronal Mass Ejections, with incremental improvements in segmentation methods.
The paper tackles the problem of accurately segmenting solar filaments in H-alpha observations to capture fine-scale structures like barbs, which is critical for determining filament chirality related to Coronal Mass Ejections. The result is that EdgeAttNet, a U-Net-based architecture with a novel learnable edge map integrated into self-attention, outperforms baselines on the MAGFILO dataset with higher segmentation accuracy and better barb recognition, while offering faster inference.
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.