MJ-COCO, a pseudo-labeling based re-annotation of MS-COCO, improves detection on some external benchmarks but reduces performance on the standard MS-COCO validation set.
A trainable pedestrian detection system,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patterns
MJ-COCO, a pseudo-labeling based re-annotation of MS-COCO, improves detection on some external benchmarks but reduces performance on the standard MS-COCO validation set.