Niemeijer, Joshua and Schäfer, P. Jörg (2021) Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation. In: IEEE Intelligent Vehicles Symposium, IV 2021. IV2021: Workshop on Autonomy@Scale, 11. Juli 2021, Nagoya, Japan.
![]() |
PDF
1MB |
Abstract
This work presents a two-staged, unsupervised domain adaptation process for semantic segmentation models by combining a self-training and self-supervision strategy. Self-training (i. e., training a model on self-inferred pseudo-labels) yields competitive results for domain adaptation in recent research. However, self-training depends on high-quality pseudo-labels. On the other hand, self-supervision trains the model on a surrogate task and improves its performance on the target domain without further prerequisites. Therefore, our approach improves the model's performance on the target domain with a novel surrogate task. To that, we continuously determine class centroids of the feature representations in the network’s pre-logit layer on the source domain. Our surrogate task clusters the pre-logit feature representations on the target domain regarding these class centroids during both training stages. After the first stage, the resulting model delivers improved pseudo-labels for the additional self-training in the second stage. We evaluate our method on two different domain adaptions, a real-world domain change from Cityscapes to the Berkeley Deep Drive dataset and a synthetic to real-world domain change from GTA5 to the Cityscapes dataset. For the real-world domain change, the evaluation shows a significant improvement of the model from 46% mIoU to 54% mIoU on the target domain. For the synthetic to real-world domain change, we achieve an improvement from 38.8% to 46.42% on the real-world target domain
Item URL in elib: | https://elib.dlr.de/143158/ | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Document Type: | Conference or Workshop Item (Speech) | |||||||||
Title: | Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation | |||||||||
Authors: |
| |||||||||
Date: | July 2021 | |||||||||
Journal or Publication Title: | IEEE Intelligent Vehicles Symposium, IV 2021 | |||||||||
Refereed publication: | Yes | |||||||||
Open Access: | Yes | |||||||||
Gold Open Access: | No | |||||||||
In SCOPUS: | No | |||||||||
In ISI Web of Science: | No | |||||||||
Status: | Published | |||||||||
Keywords: | Deep-Learning, Unsupervised-Learning; Domain Adaptation; Autonomous Vehicles; Environment Perception; Artificial Intelligence | |||||||||
Event Title: | IV2021: Workshop on Autonomy@Scale | |||||||||
Event Location: | Nagoya, Japan | |||||||||
Event Type: | international Conference | |||||||||
Event Dates: | 11. Juli 2021 | |||||||||
HGF - Research field: | Aeronautics, Space and Transport | |||||||||
HGF - Program: | Transport | |||||||||
HGF - Program Themes: | Road Transport | |||||||||
DLR - Research area: | Transport | |||||||||
DLR - Program: | V ST Straßenverkehr | |||||||||
DLR - Research theme (Project): | V - NGC KoFiF | |||||||||
Location: | Braunschweig | |||||||||
Institutes and Institutions: | Institute of Transportation Systems | |||||||||
Deposited By: | Niemeijer, Joshua | |||||||||
Deposited On: | 26 Jul 2021 16:32 | |||||||||
Last Modified: | 01 Jan 2023 03:00 |
Repository Staff Only: item control page