A detector trained with feature contrastive and uncertainty classification losses improves open-set semi-supervised object detection, labeling unseen objects as unknown.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection
A detector trained with feature contrastive and uncertainty classification losses improves open-set semi-supervised object detection, labeling unseen objects as unknown.