papers AI Learner
The Github is limit! Click to go to the new site.

Online Adaptation through Meta-Learning for Stereo Depth Estimation

2019-04-17
Zhenyu Zhang, Stéphane Lathuilière, Andrea Pilzer, Nicu Sebe, Elisa Ricci, Jian Yang

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08462

PDF

http://arxiv.org/pdf/1904.08462


Similar Posts

Comments