Diversity with Cooperation: Ensemble Methods for Few-Shot Classification
This work addresses the problem of few-shot classification for machine learning practitioners, offering a competitive alternative to meta-learning methods.
The paper tackles the high-variance issue in few-shot classification by proposing an ensemble of deep networks with cooperation and diversity strategies, achieving state-of-the-art results on mini-ImageNet and CUB datasets.
Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that advocates the ability to "learn to adapt". Recent works have shown, however, that simple learning strategies without meta-learning could be competitive. In this paper, we go a step further and show that by addressing the fundamental high-variance issue of few-shot learning classifiers, it is possible to significantly outperform current meta-learning techniques. Our approach consists of designing an ensemble of deep networks to leverage the variance of the classifiers, and introducing new strategies to encourage the networks to cooperate, while encouraging prediction diversity. Evaluation is conducted on the mini-ImageNet and CUB datasets, where we show that even a single network obtained by distillation yields state-of-the-art results.