Fast and Generalized Adaptation for Few-Shot Learning

By Liang Song, Jinlu Liu, Yongqiang Qin. 2019

8 citations recorded by the source corpus.

The ability of fast generalizing to novel tasks from a few examples is critical in dealing with few-shot learning problems. However, deep learning models severely suffer from overfitting in extreme low data regime. In this paper, we propose Adaptable Cosine Classifier (ACC) and Amphibian to achieve fast and generalized adaptation for few-shot learning. The ACC realizes the flexible retraining of a deep network on small data without overfitting. The Amphibian learns a good weight initialization in the parameter space where optimal solutions for the tasks of the same class cluster tightly. It enables rapid adaptation to novel tasks with few gradient updates. We conduct comprehensive experiments on four few-shot datasets and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existing methods by 10%. We also conduct experiment on cross-domain few-shot tasks and provide the best results.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Micah Goldblum
2. Liam H. Fowl
3. Steven Reich
4. Valeriia Cherepanova
5. Tom Goldstein
6. Renkun Ni

Citations in the corpus

• Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks (2020, background): “Recently, a number of few-shot benchmarks have been rapidly improved using meta-learning methods (Lee et al., 2019; Song et al., 2019).”