Complementary Feature Pyramid Network for Object Detection

Jin Xie

doi:10.1145/3584362

Complementary Feature Pyramid Network for Object Detection

2023-05-31

3

PRE

AI

DOI：10.1145/3584362

Original request for help

Save

Abstract

En 中文

The way of constructing a robust feature pyramid is crucial for object detection. However, existing feature pyramid methods, which aggregate multi-level features by using element-wise sum or concatenation, are inefficient to construct a robust feature pyramid. The reason is that these methods cannot be effective in discriminating the relevant semantics of objects. In this article, we propose a Complementary Feature Pyramid Network (CFPN) to aggregate multi-level features selectively and efficiently by exploring complementary information betweenmulti-level features. Specifically, a Spatial Complementary Module (SCM) and a Channel Complementary Module (CCM) are designed and embedded in CFPN to enhance useful information and suppress irrelevant information during feature fusions along spatial and channel dimensions, respectively. CFPN is a generic feature extractor, as evidenced by its seamless integration into single-stage, two-stage, and end-to-end object detectors. Experiments conducted on the COCO and Pascal VOC datasets demonstrate that integrating our CFPN into RetinaNet, Faster RCNN, Cascade RCNN, and Sparse RCNN obtains consistent performance improvements with negligible overheads. Code and models are available at: https://github.com/ VIPLab- CQU/CFPN.

Keywords:

Object detection

Feature pyramid networks

Multi-scale object detection

Complementary Feature Pyramid Network for Object Detection

Abstract

Journal

Organization