Adversarial learning for semi-supervised semantic segmentation

Wei Chih Hung, Yi Hsuan Tsai, Yan Ting Liou, Yen-Yu Lin, Ming Hsuan Yang

研究成果: Paper同行評審

132 引文 斯高帕斯(Scopus)


We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial resolution. We show that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model. In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory signals. In contrast to existing methods that utilize weakly-labeled images, our method leverages unlabeled images to enhance the segmentation model. Experimental results on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the effectiveness of the proposed algorithm.

出版狀態Published - 22 2月 2018
事件29th British Machine Vision Conference, BMVC 2018 - Newcastle, United Kingdom
持續時間: 3 9月 20186 9月 2018


Conference29th British Machine Vision Conference, BMVC 2018
國家/地區United Kingdom


深入研究「Adversarial learning for semi-supervised semantic segmentation」主題。共同形成了獨特的指紋。