当前位置 >>成果展示 >>论文

Fully Convolutional Instance-Aware Semantic Segmentation.(CVPR)时间: 2017-07-21 点击: 75 次

Authors: Yi Li ; Haozhi Qi ; Jifeng Dai ; Xiangyang Ji ; Yichen Wei

Published in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)


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 [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.

Date of Conference: 21-26 July 2017
Date Added to IEEE Xplore: 09 November 2017
INSPEC Accession Number: 17355761


上一篇:Transfer knowledge for high sparsity in deep neural networks.(GlobalSIP 2017) 下一篇:Feedback-Free Binning Design for Mobile Wyner-Ziv Video Coding: An Operational Duality between Source Distortion and Channel Capacity.( IEEE T MOBILE COMPUT 2017) 返回列表

用户登录

用户注册