Open access
2026
SenSNN: Energy-Efficient Tiny-Object Pseudo-Mask Segmentation via a Dual-Stream Membrane Shortcut
Results indicate that SenSNN provides a complementary low-energy architecture for dense tiny-object screening under constrained operation-level energy budgets, and shows that localized spiking consensus provides a more efficient tradeoff than global attention for subpixel targets.
Runxiang Wang, Hao Li, Xiqing Guo
· IEEE Journal of Selected Top... · 0 citations