(2020) Synthetic Convolutional Features for Improved Semantic Segmentation.
Abstract
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.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Mario Fritz (MF) |
| Conference: | ACVR International Workshop on Assistive Computer Vision and Robotics |
| Depositing User: | Mario Fritz |
| Date Deposited: | 04 Oct 2020 16:54 |
| Last Modified: | 12 May 2021 10:39 |
| Primary Research Area: | NRA1: Trustworthy Information Processing |
| URI: | https://publications.cispa.saarland/id/eprint/3234 |
Actions
Actions (login required)
 |
View Item |