Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation
This work addresses depth estimation for computer vision applications, presenting an incremental improvement in semi-supervised learning methodology.
The paper tackles monocular depth estimation by proposing a semi-supervised learning framework that combines sparse supervised and unsupervised loss functions through mutual distillation between two network branches, achieving improved performance over latest methods.
We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the complementary advantages of both loss functions, by building two separate network branches for each loss and distilling each other through the mutual distillation loss function. We also present to apply different data augmentation to each branch, which improves the robustness. We conduct experiments to demonstrate the effectiveness of our framework over the latest methods and provide extensive ablation studies.