Diversity with Cooperation: Ensemble Methods for Few-Shot Classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification


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, tiered-ImageNet and CUB datasets, where we show that even a single network obtained by distillation yields state-of-the-art results.
Fichier principal
Vignette du fichier
main.pdf (591.79 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02080004 , version 1 (26-03-2019)
hal-02080004 , version 2 (08-08-2019)



Nikita Dvornik, Julien Mairal, Cordelia Schmid. Diversity with Cooperation: Ensemble Methods for Few-Shot Classification. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. pp.3722-3730, ⟨10.1109/ICCV.2019.00382⟩. ⟨hal-02080004v2⟩
336 View
579 Download



Gmail Mastodon Facebook X LinkedIn More