Resource-efficient Object Detection by Sharing Backbone CNNs

The detection of objects in image and video has made huge progress in recent years due to the use of deep convolutional neural networks (DNNs), with some network architectures becoming de-facto standards. This paper addresses the problem of sharing a backbone CNN for different tasks, for example, to enable detection of additional classes when an already trained network is available. When using multiple such neural networks, sharing a backbone can save inference time and memory consumption. We study the issues of sharing a common backbone between neural networks trained for different tasks (logoness and text block detection) based on Yolo v3. We provide results on the impact of different lengths of the shared backbone on performance and resource efficiency.