Fully Convolutional Instance-aware Semantic Segmentation

TL;DR

This paper introduces a fully convolutional, end-to-end approach for instance-aware semantic segmentation that shares representations across tasks, achieving state-of-the-art results and winning the COCO 2016 competition.

Contribution

It presents the first fully convolutional network for joint instance mask prediction and classification, improving efficiency and accuracy over previous methods.

Findings

Achieved state-of-the-art performance on COCO 2016 segmentation task.

Outperformed existing methods in accuracy and efficiency.

Won the COCO 2016 segmentation competition by a large margin.

Abstract

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}.