ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation

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 re-training. 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 degrade the performance. To this end, we further propose an advanced self-training framework (namely ST++), that performs selective re-training via prioritizing reliable unlabeled images based on holistic prediction-level stability. Concretely, several model checkpoints are saved in the first stage supervised training, and the discrepancy of their predictions on the unlabeled image serves as a measurement for reliability. Our image-level selection offers holistic contextual information for learning. We demonstrate that it is more suitable for segmentation than common pixel-wise selection. As a result, ST++ further boosts the performance of our ST. Code is available at https://github.com/LiheYoung/ST-PlusPlus.

arXiv commentAccepted by CVPR 2022

References in corpus (12)

• Improved Regularization of Convolutional Neural Networks with Cutout
• Improved Baselines with Momentum Contrastive Learning
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Semi-Supervised Learning with Ladder Networks
• Rethinking Pre-training and Self-training
• Learning with Pseudo-Ensembles
• Billion-scale semi-supervised learning for image classification
• A Simple Semi-Supervised Learning Framework for Object Detection
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
• DMT: Dynamic Mutual Training for Semi-Supervised Learning
• A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation

Cited by in corpus (2)

• Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
• Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention