Better segmentation with semi-supervised learning by augmentation with AugSeg
Better segmentation with semi-supervised learning by augmentation with AugSeg
Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2212.04976
arXiv PDF paper https://arxiv.org/pdf/2212.04976.pdf
Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress.
... state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network components and additional training procedures.
... follow a standard teacher-student framework and propose AugSeg, a simple and clean approach that focuses mainly on data perturbations to boost the SSS performance.
... data augmentations should be adjusted to better adapt to the semi-supervised scenarios instead of directly applying these techniques from supervised learning.
... adopt a simplified intensity-based augmentation that selects a random number of data transformations with uniformly sampling distortion strengths from a continuous space.
... simple AugSeg can readily achieve new state-of-the-art performance on SSS benchmarks under different partition protocols.
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