ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
This addresses the problem of expensive manual labeling in semantic segmentation for applications requiring precise segmentations, offering an incremental improvement over existing semi-supervised methods.
The paper tackles the high cost of labeling for semantic segmentation by proposing ClassMix, a novel data augmentation method for semi-supervised learning that mixes unlabeled samples based on network predictions to respect object boundaries, achieving state-of-the-art results on benchmarks.
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.