.png){kind=icon}
.png){kind=icon}
Return
Augmenting Few-Shot Learning With Supervised Contrastive Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3074525.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Few-shot learning deals with a small amount of data which incurs insufficient performance with conventional cross-entropy loss. We propose a pretraining approach for few-shot learning scenarios. That is, considering that the feature extractor quality is a critical factor in few-shot learning, we augment the feature extractor using a contrastive learning technique. It is reported that supervised contrastive learning applied to base class training in transductive few-shot training pipeline leads to improved results, outperforming the state-of-the-art methods on Mini-ImageNet and CUB. Furthermore, our experiment shows that a much larger dataset is needed to retain few-shot classification accuracy when domain-shift degradation exists, and if our method is applied, the need for a large dataset is eliminated. The accuracy gain can be translated to a runtime reduction of 3.87x in a resource-constrained environment.
Keywords:
Few-shot learning
contrastive learning
information maximization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.