Multi-scale Network Architecture Search for Object Detection

Many commonly-used detection frameworks aim to handle the multi-scale object detection problem. The input image is always encoded to multi-scale features and objects grouped by scale range are assigned to the corresponding features. However, the design of multi-scale feature production is quite hand-crafted or partially automatic. In this paper, we show that more possible architectures of encoder network and different strategies of feature utilization can lead to superior performance. Specifically, we propose an efficient and effective multi-scale network architecture search method (MSNAS) to improve multi-scale object detection by jointly optimizing network stride search of the encoder and appropriate feature selection for detection heads. We demonstrate the effectiveness of the method on COCO dataset and obtain a remarkable performance gain with respect to the original Feature Pyramid Networks.