ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA

Ting-Hsuan Liao (National Tsing Hua University), Huang-Ru Liao (National Tsing Hua University), Shan-Ya Yang (National Tsing Hua University), Jie-En Yao (National Tsing Hua University), Li-Yuan Tsao (National Tsing Hua University), Hsu-Shen Liu (National Tsing Hua University), Chen-Hao Chao (National Tsing Hua University ), Bo-Wun Cheng (National Tsing Hua University), Chia-Che Chang (MediaTek Inc.), Yi-Chen Lo (MediaTek Inc.), Chun-Yi Lee (National Tsing Hua University)*
The 33rd British Machine Vision Conference


Many unsupervised domain adaptation (UDA) methods have been proposed to bridge the domain gap by utilizing domain invariant information. Most approaches have chosen depth as such information and achieved remarkable successes. Despite their effectiveness, using depth as domain invariant information in UDA tasks may lead to multiple issues, such as excessively high extraction costs and difficulties in achieving a reliable prediction quality. As a result, we introduce Edge Learning based Domain Adaptation (ELDA), a framework which incorporates edge information into its training process to serve as a type of domain invariant information. In our experiments, we quantitatively and qualitatively demonstrate that the incorporation of edge information is indeed beneficial and effective, and enables ELDA to outperform the contemporary state-of-the-art methods on two commonly adopted benchmarks for semantic segmentation based UDA tasks. In addition, we show that ELDA is able to better separate the feature distributions of different classes. We further provide ablation analysis to justify our design decisions.



author    = {Ting-Hsuan Liao and Huang-Ru Liao and Shan-Ya Yang and Jie-En Yao and Li-Yuan Tsao and Hsu-Shen Liu and Chen-Hao Chao and Bo-Wun Cheng and Chia-Che Chang and Yi-Chen Lo and Chun-Yi Lee},
title     = {ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA},
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/0108.pdf}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection