IPG-Net: Image Pyramid Guidance Network for Object Detection

For Convolutional Neural Network based object detection, there is a typical dilemma: the spatial information is well kept in the shallow layers which unfortunately do not have enough semantic information, while the deep layers have high semantic concept but lost a lot of spatial information, resulting in serious information imbalance. To acquire enough semantic information for shallow layers, Feature Pyramid Networks (FPN) is used to build a top-down propagated path. In this paper, except for top-down combining of information for shallow layers, we propose a novel network called Image Pyramid Guidance Network(IPG-Net) to make sure both the spatial information and semantic information are abundant for each layer. Our IPG-Net has three main parts: the image pyramid guidance sub-network, the ResNet based backbone network and the fusing module. The image pyramid guidance sub-network supplies spatial information to each scale's feature to solve the information imbalance problem. This sub-network promise even in the deepest stage of the ResNet, there is enough spatial information for bounding box regression and classification. Furthermore, we designed an effective fusing module to fuse the features from the image pyramid and features from the feature pyramid. We have tried to apply this novel network to both one stage and two stage models, state of the art results are obtained on the most popular benchmark data sets, i.e. MS COCO and Pascal VOC.