Fully Convolutional Instance-aware Semantic Segmentation
This work addresses the problem of instance-aware semantic segmentation for computer vision applications, representing a novel method rather than an incremental improvement.
The paper tackles instance-aware semantic segmentation by introducing the first fully convolutional end-to-end solution, which jointly predicts instance masks and classifications with shared representations, achieving state-of-the-art performance and winning the COCO 2016 segmentation competition by a large margin.
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 and instance mask proposal. 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 proposed network is highly integrated and 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 \url{https://github.com/daijifeng001/TA-FCN}.