Learning With Side Information Through Modality Hallucination

TitleLearning With Side Information Through Modality Hallucination
Publication TypeConference Paper
Year of Publication2016
AuthorsHoffman, J., Gupta S., & Darrell T.
Published inThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Page(s)826-834
Date Published06/2016
Abstract

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.

URLhttp://www.icsi.berkeley.edu/pubs/vision/modalityhallucination16.pdf