Adds refinement loss and auxiliary RPN branch to rebalance novel-class proposals, yielding 1-6% gains on few-shot detection benchmarks.
Self- supervised learning for few-shot image classification,
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
-
Proposal Refinement for Few-Shot Object Detection
Adds refinement loss and auxiliary RPN branch to rebalance novel-class proposals, yielding 1-6% gains on few-shot detection benchmarks.