Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction

12 May 2023  ·  Cho-Ying Wu, Yiqi Zhong, Junying Wang, Ulrich Neumann ·

Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied image classification in meta-learning, depth is pixel-level continuous range values, and mappings from each image to depth vary widely across environments. Thus no explicit task boundaries exist. We instead propose fine-grained task that treats each RGB-D pair as a task in our meta-optimization. We first show meta-learning on limited data induces much better prior (max +29.4\%). Using meta-learned weights as initialization for following supervised learning, without involving extra data or information, it consistently outperforms baselines without the method. Compared to most indoor-depth methods that only train/ test on a single dataset, we propose zero-shot cross-dataset protocols, closely evaluate robustness, and show consistently higher generalizability and accuracy by our meta-initialization. The work at the intersection of depth and meta-learning potentially drives both research streams to step closer to practical use.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Monocular Depth Estimation NYU-Depth V2 Meta-Initialization RMSE 0.348 # 34
absolute relative error 0.093 # 29
Delta < 1.25 0.908 # 39
Delta < 1.25^2 0.980 # 43
Delta < 1.25^3 0.995 # 41
log 10 0.043 # 37

Methods