Multi-task Self-Supervised Visual Learning
Abstract
We investigate methods for combining multiple self-supervised tasks--i.e., supervised tasks where data can be collected without manual labeling--in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and methods for "harmonizing" network inputs in order to learn a more unified representation. We evaluate all methods on ImageNet classification, PASCAL VOC detection, and NYU depth prediction. Our results show that deeper networks work better, and that combining tasks--even via a naive multi-head architecture--always improves performance. Our best joint network nearly matches the PASCAL performance of a model pre-trained on ImageNet classification, and matches the ImageNet network on NYU depth prediction.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2017
- arXiv:
- arXiv:1708.07860
- Bibcode:
- 2017arXiv170807860D
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- Published at ICCV 2017