Synthetic to Realistic Imbalanced Domain Adaption for Urban Scene Perception

Yining Hua, Dewei Yi* (Corresponding Author)

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Deep neural networks (DNNs) technique has achieved impressive performance on semantic segmentation, while its training process requires a large amount of pixel-wise labelled data. Domain adaptation, as a promising solution, can break the restriction by training the model on synthetic data, and generalising it in real-world data. However, there is still a lack of attention paid to the imbalance problems on semantic segmentation adaptation, including the imbalance problem between i) source and target data, ii) different classes. To solve these problems, a progressive hierarchical feature alignment method is proposed in this paper. To alleviate the data imbalance problem, the network is progressively trained by the data from multisource domains, so as to obtain domain-invariant features. To address the class imbalance problem, the features are aligned hierarchically across domains. According to the experimental results, our method shows the competitive adapted segmentation performance on three benchmark datasets.
Original languageEnglish
JournalIEEE Transactions on Industrial Informatics
Early online date25 Aug 2021
DOIs
Publication statusE-pub ahead of print - 25 Aug 2021

Keywords

  • Image segmentation
  • convolution neural networks
  • domain adaptation
  • deep learning

Fingerprint

Dive into the research topics of 'Synthetic to Realistic Imbalanced Domain Adaption for Urban Scene Perception'. Together they form a unique fingerprint.

Cite this