A training framework with a dual-branch decoder lets visible-infrared fusion networks learn semantic segmentation as an auxiliary task, improving fused-image segmentation without a separate cascade model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning
A training framework with a dual-branch decoder lets visible-infrared fusion networks learn semantic segmentation as an auxiliary task, improving fused-image segmentation without a separate cascade model.