Recently, learning-based image synthesis has enabled to generate high-resolution images, either applying popular adversarial training or a powerful perceptual loss. However, it remains challenging to successfully leverage synthetic data for improving semantic segmentation with additional synthetic images. Therefore, we suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. This allows us to generate new features from label masks and include them successfully into the training procedure in order to improve the performance of semantic segmentation. Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
History
Preferred Citation
Yang He, Bernt Schiele and Mario Fritz. Synthetic Convolutional Features for Improved Semantic Segmentation. In: Workshop on Assistive Computer Vision and Robotics at European Conference on Computer Vision (ECCV-Workshop). 2020.
Primary Research Area
Trustworthy Information Processing
Name of Conference
Workshop on Assistive Computer Vision and Robotics at European Conference on Computer Vision (ECCV-Workshop)
Legacy Posted Date
2020-10-04
Open Access Type
Unknown
BibTeX
@inproceedings{cispa_all_3234,
title = "Synthetic Convolutional Features for Improved Semantic Segmentation",
author = "He, Yang and Schiele, Bernt and Fritz, Mario",
booktitle="{Workshop on Assistive Computer Vision and Robotics at European Conference on Computer Vision (ECCV-Workshop)}",
year="2020",
}