Cross Modal Distillation for Supervision Transfer
2016pp. 2827–2836
Citations Over TimeTop 1% of 2016 papers
Abstract
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 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 transfer supervision from labeled RGB images to unlabeled depth and optical flow images and demonstrate large improvements for both these cross modal supervision transfers.
Related Papers
- → Factors Influencing Modality Choice in Multimodal Applications(2008)15 cited
- → About the Teaching Strategies of Modality in the Classroom(2016)1 cited
- An Analysis of Modality Orientations in College English Text Introductions(2008)
- Brief comment on modality in English(2007)
- A Preliminary Study on Modality of Chinese(2002)