Category information amount, computed from embedding covariance, guides an angular margin loss that improves long-tailed object detection on LVIS, COCO-LT, and Pascal VOC.
Image-level or object-level? a tale of two resampling strategies for long-tailed detection
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
-
Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
Category information amount, computed from embedding covariance, guides an angular margin loss that improves long-tailed object detection on LVIS, COCO-LT, and Pascal VOC.