Authors
Qibin Hou, Ming-Ming Cheng, Jiangjiang Liu, Philip HS Torr
Publication date
2018/3/27
Journal
arXiv preprint arXiv:1803.09859
Description
In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations, thus substantially alleviating the dependence on accurate annotations when compared to previous weakly supervised methods. To solve such a challenging problem, we leverage several low-level cues (such as saliency, edges, etc.) to help generate a proxy ground truth. Due to the diversity of web-crawled images, we anticipate a large amount of 'label noise' in which other objects might be present. We design an online noise filtering scheme which is able to deal with this label noise, especially in cluttered images. We use this filtering strategy as an auxiliary module to help assist the segmentation network in learning cleaner proxy annotations. Extensive experiments on the popular PASCAL VOC 2012 semantic segmentation benchmark show surprising good results in both our WebSeg (mIoU = 57.0%) and weakly supervised (mIoU = 63.3%) settings.
Total citations
2017201820192020202120222023113211
Scholar articles
Q Hou, MM Cheng, J Liu, PHS Torr - arXiv preprint arXiv:1803.09859, 2018