Generative modelling of semantic segmentation data in the fashion domain
Paper in proceeding, 2019

In this work, we propose a method to generatively model the joint distribution of images and corresponding semantic segmentation masks using generative adversarial networks. We extend the Style-GAN architecture by iteratively growing the network during training, to add new output channels that model the semantic segmentation masks. We train the proposed method on a large dataset of fashion images and our experimental evaluation shows that the model produces samples that are coherent and plausible with semantic segmentation masks that closely match the semantics in the image.

Semantic segmentations

Clothing parsing

Artificial neural networks

Henerative adversarial networks

Deep learning


Marie Korneliusson

Chalmers, Computer Science and Engineering (Chalmers), Formal methods

John Martinsson

RISE Research Institutes of Sweden

Olof Mogren

RISE Research Institutes of Sweden

Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

3169-3172 9022286

17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Seoul, South Korea,

Subject Categories

Bioinformatics (Computational Biology)

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing



More information

Latest update

5/3/2021 9