Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4353-4361

Convolution Neural Network (CNN) has boosted the per- formanceofalotofcomputervisiontasks, likeimageclassi- fication [31], segmentation [25], and detection [28]. Based on the observations from [31, 32, 14], recent model design- ers prefer to employ stacking of small kernels, like 3 x 3 over large-size filters. However, in the field of semantic seg- mentation, where we need to perform dense per-pixel pre- diction, we find that large kernel plays an important role to relieve the contradictories when optimizing the classi- fication and localization tasks simultaneously. Following the design principle of large-size kernel, We propose the Global Convolutional Network to address both the classi- fication and localization issue in the semantic segmentation task. To further refine the object category boundaries, we presentBoundaryRefinementblockbasedonresidualstruc- ture. Qualitatively, our model achieves state-of-art perfor- mance on two public benchmarks and outperforms previous results on a large margin, 82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.