Global Context Aware RCNN for Object Detection
This paper tackles the problem of lost global context information for object detection algorithms, offering an incremental improvement to existing two-stage methods.
This paper addresses the loss of global context information in RoIPool/RoIAlign processes in two-stage object detection. They propose Global Context Aware (GCA) RCNN, which fuses global context information to strengthen spatial correlation between background and foreground, demonstrating significant advantages on the COCO benchmark dataset.
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, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) 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 GCA 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 improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach.