Delving deep into the imbalance of positive proposals in two-stage object detection

Zheng Ge, Zequn Jie, Xin Huang, Chengzheng Li, Osamu Yoshie

研究成果: Article査読

1 被引用数 (Scopus)

抄録

Imbalance issue is a major yet unsolved bottleneck for the current object detection models. In this work, we observe two crucial yet never discussed imbalance issues. The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i.e., post-classification layers) become highly biased towards the negative proposals in the early training stage. The second imbalance stems from the unbalanced ground-truth numbers across different testing images, resulting in the imbalance of the number of potentially existing positive proposals in testing phase. To tackle these two imbalance issues, we incorporates two innovations into Faster R-CNN: 1) an R-CNN Gradient Annealing (RGA) strategy to enhance the impact of positive proposals in the early training stage. 2) a set of Parallel R-CNN Modules (PRM) with different positive/negative sampling ratios during training on one same backbone. Our RGA and PRM can totally bring 2.0% improvements on AP on COCO minival. Experiments on CrowdHuman further validates the effectiveness of our innovations across various kinds of object detection tasks.

本文言語English
ページ(範囲)107-116
ページ数10
ジャーナルNeurocomputing
425
DOI
出版ステータスPublished - 2021 2 15

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 認知神経科学
  • 人工知能

フィンガープリント

「Delving deep into the imbalance of positive proposals in two-stage object detection」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル