Automatic universal taxonomies for multi-domain semantic segmentation
Petra Bevandić (University of Zagreb Faculty of Electrical Engineering and Computing),* Sinisa Segvic (University of Zagreb Faculty of Electrical Engineering and Computing)
The 33rd British Machine Vision Conference
Abstract
Training semantic segmentation models on multiple datasets has sparked a lot of recent interest in the computer vision community. This interest has been motivated by expensive annotations and a desire to achieve proficiency across multiple visual domains. However, established datasets have mutually incompatible labels which disrupt principled inference in the wild. We address this issue by automatic construction of universal taxonomies through iterative dataset integration. Our method detects subset-superset relationships between dataset-specific labels, and supports learning of sub-class logits by treating super-classes as partial labels. We present experiments on collections of standard datasets and demonstrate competitive generalization performance with respect to previous work.Video
Citation
@inproceedings{Bevandić_2022_BMVC,
author = {Petra Bevandić and Sinisa Segvic},
title = {Automatic universal taxonomies for multi-domain semantic segmentation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0063.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by