Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 32, Issue 8, Pages 3458-3470Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3011526
Keywords
Task analysis; Adaptation models; Training; Predictive models; Feature extraction; Generators; Computational modeling; Few-shot learning; meta-learning; predict classifier weights; task-adaptive predictor
Categories
Funding
- National Key Research and Development Program of China [2017YFA0700800]
- Natural Science Foundation of China [61772496]
- Youth Innovation Promotion Association of Chinese Academy of Sciences [2017145]
Ask authors/readers for more resources
This article proposes a novel meta-learning method to learn task-adaptive classifier-predictor for few-shot classification, achieving state-of-the-art performance on benchmarks. By introducing a meta classifier-predictor module (MPM) and center-uniqueness loss function, the method can better capture category characteristics in novel tasks and generate more accurate and effective classifiers.
Few-shot learning aims to learn a well-performing model from a few labeled examples. Recently, quite a few works propose to learn a predictor to directly generate model parameter weights with episodic training strategy of meta-learning and achieve fairly promising performance. However, the predictor in these works is task-agnostic, which means that the predictor cannot adjust to novel tasks in the testing phase. In this article, we propose a novel meta-learning method to learn how to learn task-adaptive classifier-predictor to generate classifier weights for few-shot classification. Specifically, a meta classifier-predictor module, (MPM) is introduced to learn how to adaptively update a task-agnostic classifier-predictor to a task-specialized one on a novel task with a newly proposed center-uniqueness loss function. Compared with previous works, our task-adaptive classifier-predictor can better capture characteristics of each category in a novel task and thus generate a more accurate and effective classifier. Our method is evaluated on two commonly used benchmarks for few-shot classification, i.e., miniImageNet and tieredImageNet. Ablation study verifies the necessity of learning task-adaptive classifier-predictor and the effectiveness of our newly proposed center-uniqueness loss. Moreover, our method achieves the state-of-the-art performance on both benchmarks, thus demonstrating its superiority.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available