Delving into the Imbalance of Positive Proposals in Two-stage Object Detection

TL;DR

This paper identifies two key imbalance issues in two-stage object detection and proposes novel strategies, R-CNN Gradient Annealing and Parallel R-CNN Modules, to improve detection performance.

Contribution

It introduces two innovative methods to address imbalance problems in two-stage object detection, enhancing accuracy and robustness.

Findings

Achieved 2.0% AP improvement on COCO minival.

Validated effectiveness across various object detection tasks.

Demonstrated improvements with proposed methods on multiple datasets.

Abstract

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.