Learning with Side Information through Modality Hallucination

We present a modality hallucination architecture for training an RGB object detection model which incorporates depth side information at training time. Our convolutional hallucination network learns a new and complementary RGB image representation which is taught to mimic convolutional mid-level fea...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 826 - 834
Main Authors Hoffman, Judy, Gupta, Saurabh, Darrell, Trevor
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Computer architecture
Data mining
Feature extraction
Image recognition
Object detection
Training
Online AccessGet full text

Cover

More Information
Summary:We present a modality hallucination architecture for training an RGB object detection model which incorporates depth side information at training time. Our convolutional hallucination network learns a new and complementary RGB image representation which is taught to mimic convolutional mid-level features from a depth network. At test time images are processed jointly through the RGB and hallucination networks to produce improved detection performance. Thus, our method transfers information commonly extracted from depth training data to a network which can extract that information from the RGB counterpart. We present results on the standard NYUDv2 dataset and report improvement on the RGB detection task.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.96