FuTCR improves new-class panoptic quality by up to 28% in continual panoptic segmentation by discovering future-like regions in background areas and applying targeted contrast and repulsion to restructure representations.
The devil is in the object boundary: Towards annotation-free instance segmentation using foundation models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
ViTs exhibit lazy aggregation by relying on irrelevant background patches for global semantics, and selectively integrating patch features into the CLS token reduces this effect and improves results across label-, text-, and self-supervision.
citing papers explorer
-
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
FuTCR improves new-class panoptic quality by up to 28% in continual panoptic segmentation by discovering future-like regions in background areas and applying targeted contrast and repulsion to restructure representations.
-
Vision Transformers Need More Than Registers
ViTs exhibit lazy aggregation by relying on irrelevant background patches for global semantics, and selectively integrating patch features into the CLS token reduces this effect and improves results across label-, text-, and self-supervision.