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

ArXi:2603.20729v1 Announce Type: cross 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