FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories.
Ssul: Semantic segmentation with unknown label for exemplar-based class-incremental learning.Advances in neural information processing systems, 34:10919–10930
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
-
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories.