Few-Shot Object Detection With Self-Supervising and Cooperative Classifier

Few-shot object detection (FSOD), which detects novel objects with only a few training instances, has recently attracted more attention. Previous works focus on making the most use of label information of objects. Still, they fail to consider the structural and semantic information of the image itself and solve the misclassification between data-abundant base classes and data-scarce novel classes efficiently. In this article, we propose FSOD with Self-Supervising and Cooperative Classifier (
$\text {F}\text {S}^{3}\text {C}$
) approach to deal with those concerns. Specifically, we analyze the underlying performance degradation of novel classes in FSOD and discover that false-positive samples are the main reason. By looking into these false-positive samples, we further notice that misclassifying novel classes as base classes are the main cause. Thus, we introduce double RoI heads into the existing Fast-RCNN to learn more specific features for novel classes. We also consider using self-supervised learning (SSL) to learn more structural and semantic information. Finally, we propose a cooperative classifier (CC) with the base–novel regularization to maximize the interclass variance between base and novel classes. In the experiment,
$\text {F}\text {S}^{3}\text {C}$
outperforms all the latest baselines in most cases on PASCAL VOC and COCO.