Fully Convolutional Instance-Aware Semantic Segmentation

Yi Li, Haozhi Qi, Jifeng Dai et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2017

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation [29] and instance mask proposal [5]. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The network architecture is highly integrated and efficient. It achieves state-of-the-art performance in both accuracy and efficiency. It wins the COCO 2016 segmentation competition by a large margin. Code would be released at https://github.com/daijifeng001/TA-FCN.

Cited by 1,071 works. doi:10.1109/cvpr.2017.472 Open-access PDF

Authors

References