Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network
This work addresses the specific challenge of enhancing border accuracy in semantic segmentation for applications like autonomous driving, representing an incremental improvement over existing methods.
The paper tackles the problem of improving semantic segmentation by refining border outlines using a graph convolutional network (GCN) on pre-segmented outputs, achieving a test set performance of 81.96% mIoU on the CamVid dataset, which is 0.404% higher than the reported state-of-the-art.
We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN). The semantic segmentation network such as Unet or DeepLabV3+ is used as a base network to have pre-segmented output. This output is converted into a graphical structure and fed into the GCN to improve the border pixel prediction of the pre-segmented output. We explored and studied the factors such as border thickness, number of edges for a node, and the number of features to be fed into the GCN by performing experiments. We demonstrate the effectiveness of the Border-SegGCN on the CamVid and Carla dataset, achieving a test set performance of 81.96% without any post-processing on CamVid dataset. It is higher than the reported state of the art mIoU achieved on CamVid dataset by 0.404%