A training-only contrastive auxiliary branch with a linearly decaying loss weight improves video object detection accuracy by about two mAP points on ImageNet VID without increasing inference cost.
Computer Vision and Image Understanding219, 103406 (2022)
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
-
Contrastive Learning through Auxiliary Branch for Video Object Detection
A training-only contrastive auxiliary branch with a linearly decaying loss weight improves video object detection accuracy by about two mAP points on ImageNet VID without increasing inference cost.