Deep Active Learning from Multispectral Data Through Cross-Modality Prediction Inconsistency

Data from multiple sensors provide independent and complementary information, which may improve the robustness and reliability of scene analysis applications. While there exist many large-scale labelled benchmarks acquired by a single sensor, collecting labelled multi-sensor data is more expensive a...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Heng, Fromont, Elisa, Lefevre, Sebastien, Avignon, Bruno
Format: Conference Proceeding
Language:English
Subjects:
Active learning
Image analysis
Image segmentation
Manuals
multiple sensor fusion
multispectral pedestrian detection
Redundancy
Robustness
semantic segmentation
Sensor fusion
Sensors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data from multiple sensors provide independent and complementary information, which may improve the robustness and reliability of scene analysis applications. While there exist many large-scale labelled benchmarks acquired by a single sensor, collecting labelled multi-sensor data is more expensive and time-consuming. In this work, we explore the construction of an accurate multispectral (here, visible & thermal cameras) scene analysis system with minimal annotation efforts via an active learning strategy based on the cross-modality prediction inconsistency. Experiments on multispectral datasets and vision tasks demonstrate the effectiveness of our method. In particular, with only 10% of labelled data on KAIST multispectral pedestrian detection dataset, we obtain comparable performance as other fully supervised State-of-the-Art methods.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506322