Learning image representations equivariant to ego-motion. (arXiv:1505.02206v1 [cs.CV])

Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsupervised regularization in convolutional neural networks to learn visual representations from egocentric video. Specifically, we enforce that our learned features exhibit equivariance i.e. they respond systematically to transformations associated with distinct ego-motions. With three datasets, we show that our unsupervised feature learning system significantly outperforms previous approaches on visual recognition and next-best-view prediction tasks. In the most challenging test, we show that features learned from video captured on an autonomous driving platform improve large-scale scene recognition in a disjoint domain.

from cs.AI updates on arXiv.org http://ift.tt/1G1849O
via IFTTT