Towards Human-Like Interpretable Object Detection Via Spatial Relation Encoding

The performance of recent deep neural networks in various computer vision areas such as object detection has increased significantly. Along with such advances, attempts to visualize and interpret the networks have been made in order to understand how a network predicts a certain result. However, there is a lack of research on ways to improve the interpretability of networks’ features. In this paper, we propose a spatial relation reasoning (SRR) framework to encode interpretable networks’ features, especially an object detector, by mimicking the human visual cognition system. The SRR consists of the spatial feature encoder (SFE) and the graph-based spatial relation encoder (GSRE) to consider spatial relationships between different parts of an object. So that, object detectors can encode spatially-related object features enabling humanlike visual interpretation. We verified the proposed framework with general object detectors on public datasets-PAS-CAL VOC and MS COCO.