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.
Long-tail Detection with Effective Class-Margins
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called \textbf{Effective Class-Margin Loss} (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at \url{https://github.com/janghyuncho/ECM-Loss}.
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.