DeSimPL reduces the share of easy pseudo-labels during self-labeling domain-adaptive detection, improving SimROD by 2 to 5 mAP on four benchmarks.
Spatially invariant unsupervised object detection with convolutional neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection
DeSimPL reduces the share of easy pseudo-labels during self-labeling domain-adaptive detection, improving SimROD by 2 to 5 mAP on four benchmarks.