Residual Bi-Fusion Feature Pyramid Network for Accurate Single-shot Object Detection

TL;DR

This paper introduces a residual bi-fusion feature pyramid network that enhances object detection accuracy across scales by effectively combining deep and shallow features in a bidirectional manner, outperforming existing methods.

Contribution

It proposes a novel residual bi-fusion feature pyramid that improves multi-scale detection accuracy and ease of training, especially with deeper backbones.

Findings

Achieved state-of-the-art results on VOC and MS COCO datasets.

Improved detection accuracy for both small and large objects.

Enhanced training stability with deeper network layers.

Abstract

State-of-the-art (SoTA) models have improved the accuracy of object detection with a large margin via a FP (feature pyramid). FP is a top-down aggregation to collect semantically strong features to improve scale invariance in both two-stage and one-stage detectors. However, this top-down pathway cannot preserve accurate object positions due to the shift-effect of pooling. Thus, the advantage of FP to improve detection accuracy will disappear when more layers are used. The original FP lacks a bottom-up pathway to offset the lost information from lower-layer feature maps. It performs well in large-sized object detection but poor in small-sized object detection. A new structure "residual feature pyramid" is proposed in this paper. It is bidirectional to fuse both deep and shallow features towards more effective and robust detection for both small-sized and large-sized objects. Due to the "residual" nature, it can be easily trained and integrated to different backbones (even deeper or lighter) than other bi-directional methods. One important property of this residual FP is: accuracy improvement is still found even if more layers are adopted. Extensive experiments on VOC and MS COCO datasets showed the proposed method achieved the SoTA results for highly-accurate and efficient object detection..