A point-supervised detector with a two-phase denoising teacher-student pipeline achieves state-of-the-art results on tiny object datasets from noisy point annotations.
IEEE Transactions on Neural Networks and Learning Systems 35(6), pp
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
-
Tiny Object Detection with Single Point Supervision
A point-supervised detector with a two-phase denoising teacher-student pipeline achieves state-of-the-art results on tiny object datasets from noisy point annotations.