A teacher-student unsupervised detector with adaptive pseudo-label mixing and small-object zoom refinement sets new state-of-the-art results on four camouflaged object detection benchmarks without using any pixel labels.
Structure-measure: A new way to evaluate fore- ground maps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
A teacher-student unsupervised detector with adaptive pseudo-label mixing and small-object zoom refinement sets new state-of-the-art results on four camouflaged object detection benchmarks without using any pixel labels.