Personalized Image Semantic Segmentation

Yu Zhang, Chang-Bin Zhang, Peng-Tao Jiang, Ming-Ming Cheng, Feng Mao; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 10549-10559


Semantic segmentation models trained on public datasets have achieved great success in recent years. However, these models didn't consider the personalization issue of segmentation though it is important in practice. In this paper, we address the problem of personalized image segmentation. The objective is to generate more accurate segmentation results on unlabeled personalized images by investigating the data's personalized traits. To open up future research in this area, we collect a large dataset containing various users' personalized images called PSS (Personalized Semantic Segmentation). We also survey some recent researches related to this problem and report their performance on our dataset. Furthermore, by observing the correlation among a user's personalized images, we propose a baseline method that incorporates the inter-image context when segmenting certain images. Extensive experiments show that our method outperforms the existing methods on the proposed dataset. The code and the PSS dataset are available at

Related Material

[pdf] [arXiv]
@InProceedings{Zhang_2021_ICCV, author = {Zhang, Yu and Zhang, Chang-Bin and Jiang, Peng-Tao and Cheng, Ming-Ming and Mao, Feng}, title = {Personalized Image Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {10549-10559} }