0

Real-time self-adaptive deep stereo

A new real-time self-adaptive deep stereo system achieves competitive performance on heterogeneous datasets through a lightweight architecture and modular adaptation algorithm.

Year
2018
Venue
real-time-self-adaptive-deep-stereo-1
Authors
5
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1810.05424v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs. These models, however, suffer from a notable decrease in accuracy when exposed to scenarios significantly different from the training set, e.g., real vs synthetic images, etc.). We argue that it is extremely unlikely to gather enough samples to achieve effective training/tuning in any target domain, thus making this setup impractical for many applications. Instead, we propose to perform unsupervised and continuous online adaptation of a deep stereo network, which allows for preserving its accuracy in any environment. However, this strategy is extremely computationally demanding and thus prevents real-time inference. We address this issue introducing a new lightweight, yet effective, deep stereo architecture, Modularly ADaptive Network (MADNet) and developing a Modular ADaptation (MAD) algorithm, which independently trains sub-portions of the network. By deploying MADNet together with MAD we introduce the first real-time self-adaptive deep stereo system enabling competitive performance on heterogeneous datasets.

Authors

5