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

by   Ping-Yang Chen, et al.

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..


MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection

Feature pyramids are widely exploited in many detectors to solve the sca...

NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection

Due to the advantages of real-time detection and improved performance, s...

Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection

Recent years have witnessed many exciting achievements for object detect...

Effective Fusion Factor in FPN for Tiny Object Detection

FPN-based detectors have made significant progress in general object det...

Residual Feature Pyramid Network for Enhancement of Vascular Patterns

The accuracy of finger vein recognition systems gets degraded due to low...

SFPN: Synthetic FPN for Object Detection

FPN (Feature Pyramid Network) has become a basic component of most SoTA ...

IPG-Net: Image Pyramid Guidance Network for Object Detection

For Convolutional Neural Network based object detection, there is a typi...

Please sign up or login with your details

Forgot password? Click here to reset