ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
Paper in proceeding, 2021

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes.

semantic segmentation

semi-supervised learning

data augmentation

Author

Viktor Olsson

Student at Chalmers

Volvo Cars

Wilhelm Tranheden

Volvo Cars

Student at Chalmers

Lennart Svensson

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Signal Processing

Juliano Pinto

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Signal Processing

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

0000-0000 (ISSN)

IEEE/CVF Winter Conference on Applications of Computer Vision
Online, Japan,

Probabilistic models and deep learning - bridging the gap

Wallenberg AI, Autonomous Systems and Software Program, -- .

Subject Categories

Computer Science

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing

DOI

10.1109/WACV48630.2021.00141

More information

Latest update

10/14/2021