Cross Modal Distillation for Supervision Transfer
This work addresses the challenge of limited labeled data for new modalities in computer vision, though it is incremental as it builds on existing distillation techniques.
The paper tackles the problem of learning representations for unlabeled modalities by transferring supervision from a labeled modality, achieving large improvements in cross-modal supervision transfers from RGB to depth and optical flow images.
In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled paired modality. Our method enables learning of rich representations for unlabeled modalities and can be used as a pre-training procedure for new modalities with limited labeled data. We show experimental results where we transfer supervision from labeled RGB images to unlabeled depth and optical flow images and demonstrate large improvements for both these cross modal supervision transfers. Code, data and pre-trained models are available at https://github.com/s-gupta/fast-rcnn/tree/distillation