Abstract | ||
---|---|---|
Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast optimization-based meta-learning method for few-shot classification. It consists of an embedding network, providing a general representation of the image, and a base learner module. The latter learns a linear classifier during the inference through an unrolled optimization procedure. We design an inner learning objective composed of (i) a robust classification loss on the support set and (ii) an entropy loss, allowing transductive learning from unlabeled query samples. By employing an efficient initialization module and a Steepest Descent based optimization algorithm, our base learner predicts a powerful classifier within only a few iterations. Further, our strategy enables important aspects of the base learner objective to be learned during meta-training. To the best of our knowledge, this work is the first to integrate both induction and transduction into the base learner in an optimization-based meta-learning framework. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach on four few-shot classification datasets. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICRA48506.2021.9561269 | 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) |
DocType | Volume | Issue |
Conference | 2021 | 1 |
ISSN | Citations | PageRank |
1050-4729 | 0 | 0.34 |
References | Authors | |
1 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ardhendu Shekhar Tripathi | 1 | 1 | 1.36 |
Danelljan Martin | 2 | 1344 | 49.35 |
Luc Van Gool | 3 | 27566 | 1819.51 |
Radu Timofte | 4 | 1880 | 118.45 |