Online Adaptation through Meta-Learning for Stereo Depth Estimation
This addresses the problem of domain shift in stereo depth estimation for autonomous driving applications, but it is incremental as it builds on existing meta-learning and feature alignment techniques.
The paper tackles online adaptation for stereo depth estimation by proposing OMLA, a meta-learning model with feature alignment, which adapts faster to new environments and achieves competitive performance with batch-trained state-of-the-art methods on the KITTI dataset.
In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, we propose a novel Online Meta-Learning model with Adaption (OMLA). Our proposal is based on two main contributions. First, to reducethe domain-shift between source and target feature distributions we introduce an online feature alignment procedurederived from Batch Normalization. Second, we devise a meta-learning approach that exploits feature alignment forfaster convergence in an online learning setting. Additionally, we propose a meta-pre-training algorithm in order toobtain initial network weights on the source dataset whichfacilitate adaptation on future data streams. Experimentally, we show that both OMLA and meta-pre-training helpthe model to adapt faster to a new environment. Our proposal is evaluated on the wellestablished KITTI dataset,where we show that our online method is competitive withstate of the art algorithms trained in a batch setting.