Extended Feature Pyramid Network for Small Object Detection

Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose an extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we introduce a cross resolution distillation mechanism to transfer the ability of perceiving details across the scales of the network, where a foreground-background-balanced loss function is designed to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100 K and small category of general object detection dataset MS COCO.

Automated summary

In this paper, the authors propose an extended feature pyramid network (EFPN) for small object detection. They introduce a feature texture transfer (FTT) module for super-resolving features and extracting regional details, as well as a cross resolution distillation mechanism to enhance the network's ability to perceive details. Experimental results show that the proposed EFPN is computationally and memory efficient, and achieves state-of-the-art results on small object detection datasets.