Attention Forest for Semantic Segmentation
Semantic segmentation is a classical task in computer vision.In this paper,we target to address the low confidence regions which traditional CNN can not solve very well in semantic segmentation task.Depending on different characteristics of low confidence regions,an adaptive and robust attention mechanism is important to focus on the informative regions but ignore the noisy parts in the image.Intuitively,one attention map only is not sufficient to model the interaction between the low confidence regions and its surrounding patches.Thus,in this paper,we propose an Attention Forest structure,a novel and robust attention mechanism,to handle the low confidence regions.Each Attention Tree structure can capture more interactions between current patches with its adjacent regions.Experiments on PASCAL VOC 2012 Dataset validate the effectiveness of our proposed algorithm.
Semantic segmentation Deep learning Attention mechanism
Jingbo Wang Yajie Xing Gang Zeng
Key Laboratory of Machine Perception, Peking University, Beijing 100871, China
国际会议
广州
英文
550-561
2018-11-23（万方平台首次上网日期，不代表论文的发表时间）