Zero Cost Improvements for General Object Detection Network

TL;DR

This paper introduces two zero-cost modules, SA-FPN and Seq-HEAD, that improve object detection accuracy without increasing computational load, applicable to various modern detection networks.

Contribution

The paper proposes novel zero-cost modules for feature fusion and detection head design, enhancing accuracy without additional computation in object detection networks.

Findings

SA-FPN improves multi-level feature fusion efficiency.

Seq-HEAD enhances classification and regression head correlation.

Networks surpass original performance by 1.1 and 0.8 AP without extra cost.

Abstract

Modern object detection networks pursuit higher precision on general object detection datasets, at the same time the computation burden is also increasing along with the improvement of precision. Nevertheless, the inference time and precision are both critical to object detection system which needs to be real-time. It is necessary to research precision improvement without extra computation cost. In this work, two modules are proposed to improve detection precision with zero cost, which are focus on FPN and detection head improvement for general object detection networks. We employ the scale attention mechanism to efficiently fuse multi-level feature maps with less parameters, which is called SA-FPN module. Considering the correlation of classification head and regression head, we use sequential head to take the place of widely-used parallel head, which is called Seq-HEAD module. To evaluate the effectiveness, we apply the two modules to some modern state-of-art object detection networks, including anchor-based and anchor-free. Experiment results on coco dataset show that the networks with the two modules can surpass original networks by 1.1 AP and 0.8 AP with zero cost for anchor-based and anchor-free networks, respectively. Code will be available at https://git.io/JTFGl.