SINGLE SHOT OBJECT DETECTION WITH TOP-DOWN REFINEMENT

General object detection is one of the most challenging tasks in computer vision for it requires both high running speed and detection accuracy. In this paper, we propose a single shot object detector with top-down refinement, denoted as SSDTOR. It not only runs at high speed and also detects multi scale objects accurately. Concretely, original SSD directly adopts the built-in multi-scale hierarchy of convolutional neural networks for detection. However, object detection needs high semantic knowledge to recognise objects while low-level convolutional features do not have. We thus build a sequence of top-down refinement modules to transmit semantic knowledge backward such that all layers have rich semantics. Experiments on PASCAL VOC 2007 and 2012 demonstrate that our network achieves competitive results both in speed and accuracy compared to other VGG16 based networks.