[2603.20729] Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.20729 (cs) [Submitted on 21 Mar 2026] Title:Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention Authors:Jose Luis Lima de Jesus Silva View a PDF of the paper titled Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention, by Jose Luis Lima de Jesus Silva View PDF HTML (experimental) Abstract:Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert annotations are rarely available and subsurface information is intrinsically multimodal. The challenge is developing weakly supervised methods combining two-dimensional image texture with depth-aligned one-dimensional well-logs. Here, we introduce a weakly supervised multimodal segmentation framework that refines threshold-guided pseudo-labels through learned models. This preserves the annotation-free character of classical thresholding and clustering workflows while extending them with denoising, confidence-aware pseudo-supervision, and physically structured fusion. We establish that threshold-guided learned refinement provides the most robust improvement over raw thresholding, denoised thresholding, and latent clustering baselines. Multimodal performance depends strongly on fusion strategy: direct concatenation provides limited gains, whereas depth-aware cross-attention, gated ...