Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

Recently, neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on image classification tasks. However, the architecture searched through the classification task is sub-optimal because of the gap between the task of classification and object detection. While work focuses on backbone network architecture search for mobile device object detection is limited, mainly because the backbone always requires expensive ImageNet pre-training. Accordingly, it is necessary to study the approach of network architecture search for mobile device object detection without expensive pre-training. In this work, we propose a backbone network architecture search algorithm which is a kind of evolutionary optimized method based on non-dominated sorting for NAS scenarios. It can quickly search the backbone network architecture within certain computational complexity constraints. It better solves the problem of suboptimal linear combination accuracy and computational cost. The proposed approach can search the backbone networks with different depths, widths, or expansion sizes via a technique of weight mapping, making it possible to apply the architecture search method for mobile device detection tasks more efficiently. In our experiments, we verify the effectiveness of the proposed approach on YoloX-Lite, a lightweight version of the object detection framework. Under similar computational complexity, the accuracy of the backbone network architecture is 2.0% mAP higher than MobileDet. Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network. To prove its effectiveness, a series of ablation studies have been carried out and the working mechanism has been analyzed in detail.