GSACP performs online point-to-mask supervision via in-batch feature-affinity propagation for single-point IRSTD, reaching 0.6674 mIoU and 38% fewer false positives on SIRST3 while mapping self-referential drift limits.
Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection
GSACP performs online point-to-mask supervision via in-batch feature-affinity propagation for single-point IRSTD, reaching 0.6674 mIoU and 38% fewer false positives on SIRST3 while mapping self-referential drift limits.