Road scenes segmentation across different domains by disentangling latent representations
Open Access
- 15 April 2023
- journal article
- research article
- Published by Springer Nature in The Visual Computer
- Vol. 40 (2) , 811-830
Abstract
Deep learning models obtain impressive accuracy in road scene understanding; however, they need a large number of labeled samples for their training. Additionally, such models do not generalize well to environments where the statistical properties of data do not perfectly match those of training scenes, and this can be a significant problem for intelligent vehicles. Hence, domain adaptation approaches have been introduced to transfer knowledge acquired on a label-abundant source domain to a related label-scarce target domain. In this work, we design and carefully analyze multiple latent space-shaping regularization strategies that work together to reduce the domain shift. More in detail, we devise a feature clustering strategy to increase domain alignment, a feature perpendicularity constraint to space apart features belonging to different semantic classes, including those not present in the current batch, and a feature norm alignment strategy to separate active and inactive channels. In addition, we propose a novel evaluation metric to capture the relative performance of an adapted model with respect to supervised training. We validate our framework in driving scenarios, considering both synthetic-to-real and real-to-real adaptation, outperforming previous feature-level state-of-the-art methods on multiple road scenes benchmarks.Keywords
All Related Versions
Funding Information
- Ministero dell’Università e della Ricerca (Law 232/2016)
- Università degli Studi di Padova (SID2020 Semantic Segmentation in the Wild)
This publication has 64 references indexed in Scilit:
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Playing for Data: Ground Truth from Computer Games2016
- The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes2016
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Semantic object classes in video: A high-definition ground truth databasePattern Recognition Letters, 2009