Learning to Exploit Multiple Vision Modalities by Using Grafted Networks


METADATA ONLY
Loading...

Date

2020

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Novel vision sensors such as thermal, hyperspectral, polarization, and event cameras provide information that is not available from conventional intensity cameras. An obstacle to using these sensors with current powerful deep neural networks is the lack of large labeled training datasets. This paper proposes a Network Grafting Algorithm (NGA), where a new front end network driven by unconventional visual inputs replaces the front end network of a pretrained deep network that processes intensity frames. The self-supervised training uses only synchronously-recorded intensity frames and novel sensor data to maximize feature similarity between the pretrained network and the grafted network. We show that the enhanced grafted network reaches competitive average precision (AP 50 ) scores to the pretrained network on an object detection task using thermal and event camera datasets, with no increase in inference costs. Particularly, the grafted network driven by thermal frames showed a relative improvement of 49.11% over the use of intensity frames. The grafted front end has only 5–8% of the total parameters and can be trained in a few hours on a single GPU equivalent to 5% of the time that would be needed to train the entire object detector from labeled data. NGA allows new vision sensors to capitalize on previously pretrained powerful deep models, saving on training cost and widening a range of applications for novel sensors.

Publication status

published

Book title

Computer Vision – ECCV 2020

Volume

12361

Pages / Article No.

85 - 101

Publisher

Springer

Event

16th European Conference on Computer Vision (ECCV 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Network Grafting Algorithm; Self-supervised learning; Thermal camera; Event-based vision; Object detection

Organisational unit

02533 - Institut für Neuroinformatik / Institute of Neuroinformatics

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

Related publications and datasets