Better segment objects in new domain by randomize style of training data with ISSA
Better segment objects in new domain by randomize style of training data with ISSA
Intra-Source Style Augmentation for Improved Domain Generalization
arXiv paper abstract https://arxiv.org/abs/2210.10175v1
arXiv PDF paper https://arxiv.org/pdf/2210.10175v1.pdf
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models.
... propose an intra-source style augmentation (ISSA) method to improve domain generalization in semantic segmentation ... based on a novel masked noise encoder for StyleGAN2 inversion.
The model learns to faithfully reconstruct the image preserving its semantic layout through noise prediction.
Random masking of the estimated noise enables the style mixing capability of ... model, i.e. it allows to alter the global appearance without affecting the semantic layout of an image.
Using the proposed masked noise encoder to randomize style and content combinations in the training set, ISSA effectively increases the diversity of training data and reduces spurious correlation.
... achieve up to 12.4% mIoU improvements on driving-scene semantic segmentation under different types of data shifts, i.e., changing geographic locations, adverse weather conditions, and day to night ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments