Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation release_ppxlgrynnza55ldn4nkqag44ey

by Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen, Ian Reid

Released as a article .

2017  

Abstract

Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation. In contrast, web images and their image-level labels are much easier and cheaper to obtain. In this work, we propose a novel method for weakly supervised semantic segmentation with only image-level labels. The method utilizes the internet to retrieve a large number of images and uses a large scale co-segmentation framework to generate masks for the retrieved images. We first retrieve images from search engines, e.g. Flickr and Google, using semantic class names as queries, e.g. class names in the dataset PASCAL VOC 2012. We then use high quality masks produced by co-segmentation on the retrieved images as well as the target dataset images with image level labels to train segmentation networks. We obtain an IoU score of 56.9 on test set of PASCAL VOC 2012, which reaches the state-of-the-art performance.
In text/plain format

Archived Files and Locations

application/pdf  5.1 MB
file_nobxhiv53jbkdfgovbjuh5nnf4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-08-06
Version   v3
Language   en ?
arXiv  1705.09052v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b97c1045-fb67-45ef-8105-faf338ffbfb0
API URL: JSON