Extended Feature Pyramid Network for Small Object Detection
This addresses the problem of detecting small objects in images for applications like traffic sign recognition, though it appears incremental as it builds on existing feature pyramid networks.
The paper tackles the challenge of small object detection by proposing an Extended Feature Pyramid Network (EFPN) that adds a high-resolution pyramid level and uses a feature texture transfer module to super-resolve features, achieving state-of-the-art results on datasets like Tsinghua-Tencent 100K and MS COCO.
Small object detection remains an unsolved challenge because it is hard to extract 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 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 design a foreground-background-balanced loss function 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 100K and small category of general object detection dataset MS COCO.