ST++: Make Self-trainingWork Better for Semi-supervised Semantic Segmentation
Nanjing University · Tencent (China)
Abstract
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student. With this simple mechanism, our ST outperforms all existing methods without any bells and whistles, e.g., iterative retraining. Inspired by the impressive results, we thoroughly investigate the SDA and provide some empirical analysis. Nevertheless, incorrect pseudo labels are still prone to accumulate and…
Citation impact
- FWCI
- 25.85
- Percentile
- 100%
- References
- 105
Authors
5Topics & keywords
- Computer science
- Overfitting
- Leverage (statistics)
- Artificial intelligence
- Segmentation
- Machine learning
- Code (set theory)
- Pipeline (software)
- Quality Education