Wenxi Liu

Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation

2024 · arXiv (Cornell University)

In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively …