Depth Jitter: Seeing through the Depth
This work addresses the problem of improving generalization for computer vision models in depth-sensitive applications such as underwater imaging and robotics, though it is incremental as it builds on existing augmentation strategies.
The paper tackles the problem of limited model robustness in real-world depth variations by introducing Depth-Jitter, a depth-based augmentation technique that simulates natural depth variations, resulting in consistent enhancements in model stability and generalization in depth-sensitive environments, as demonstrated on benchmark datasets like FathomNet and UTDAC2020.
Depth information is essential in computer vision, particularly in underwater imaging, robotics, and autonomous navigation. However, conventional augmentation techniques overlook depth aware transformations, limiting model robustness in real world depth variations. In this paper, we introduce Depth-Jitter, a novel depth-based augmentation technique that simulates natural depth variations to improve generalization. Our approach applies adaptive depth offsetting, guided by depth variance thresholds, to generate synthetic depth perturbations while preserving structural integrity. We evaluate Depth-Jitter on two benchmark datasets, FathomNet and UTDAC2020 demonstrating its impact on model stability under diverse depth conditions. Extensive experiments compare Depth-Jitter against traditional augmentation strategies such as ColorJitter, analyzing performance across varying learning rates, encoders, and loss functions. While Depth-Jitter does not always outperform conventional methods in absolute performance, it consistently enhances model stability and generalization in depth-sensitive environments. These findings highlight the potential of depth-aware augmentation for real-world applications and provide a foundation for further research into depth-based learning strategies. The proposed technique is publicly available to support advancements in depth-aware augmentation. The code is publicly available on \href{https://github.com/mim-team/Depth-Jitter}{github}.