Abstract

We present a modality hallucination architecture fortraining an RGB object detection model which incorporates depth side information at training time. Our convolutional hallucination network learns a new and com-plementary 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 infor-mation commonly extracted from depth training data to anetwork 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.