Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation  

作　　者：ZHANG Zhe WANG Bilin YU Zhezhou LI Zhiyuan 

机构地区：[1]College of Computer Science and Technology,Jilin University,Changchun 130012,China [2]Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry,Changchun 130012,China

出　　处：《Chinese Journal of Electronics》2021年第6期1120-1130,共11页电子学报（英文版）

基　　金：supported by the Development Project of Jilin Province of China (No.20200801033GH, No.2020122328JC);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education;Jilin University (No.20180520017JH);the Fundamental Research Funds for the Central Universities,JLU。

摘　　要：This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed regions of each interest target as pseudo-labels for training segmentation networks, which achieve inferior performance compared with the fully supervised setting.We propose a Dilated convolutional pixels affinity network(DCPAN) to localize and expand the seed regions of objects to bridge this gap. Although introduced dilated convolutional units enable capture of additional location information of objects, it falsely highlighted true negative regions as dilated rate enlarge. To address this problem,we properly integrate dilated convolutional units with different dilated rates and self-attention mechanisms to obtain pixel affinity measure matrix for promoting classification network to generate high-quality object seed regions as pseudo-labels;thus, the performance of the segmentation network is boosted. Furthermore,although our approach seems simple, our method obtains a competitive performance, and experiments show that the performance of DCPAN outperforms other state-ofart approaches in weakly-supervised settings, which only use image-level labels on the Pascal VOC 2012 dataset.

关 键 词：Weakly supervised Semantic segmentation Convolutional neural networks Dilated convolution Self-attention mechanism 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]