Dense Global Context Aware RCNN for Object Detection

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, in this paper, we propose a novel end-to-end trainable framework, called Dense Global Context Aware (DGCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our DGCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to fuse the global context information of different stages in the top-down process of FPN, and further leverage the attention mechanism to perform global context aware. Thus, the implicit relationship between object proposal and global features can be captured by neural networks to improve detection performance. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach.