Deep Metric Transfer for Label Propagation with Limited Annotated Data
This addresses the challenge of limited annotated data for object recognition, offering a generic solution that benefits researchers and practitioners in computer vision, though it appears incremental as it combines existing techniques like metric learning and label propagation.
The paper tackles the problem of object recognition with very few labeled examples per class by proposing a framework that uses label propagation from labeled to unlabeled data, showing it is highly effective when the similarity metric is transferred from related domains, achieving significant improvements on semi-supervised learning, transfer learning, and few-shot recognition tasks.
We study object recognition under the constraint that each object class is only represented by very few observations. Semi-supervised learning, transfer learning, and few-shot recognition all concern with achieving fast generalization with few labeled data. In this paper, we propose a generic framework that utilizes unlabeled data to aid generalization for all three tasks. Our approach is to create much more training data through label propagation from the few labeled examples to a vast collection of unannotated images. The main contribution of the paper is that we show such a label propagation scheme can be highly effective when the similarity metric used for propagation is transferred from other related domains. We test various combinations of supervised and unsupervised metric learning methods with various label propagation algorithms. We find that our framework is very generic without being sensitive to any specific techniques. By taking advantage of unlabeled data in this way, we achieve significant improvements on all three tasks.