A Universal Representation Transformer Layer for Few-Shot Image Classification

Publication Type:
Journal Article
Citation:
2020
Issue Date:
2020-06-21
Filename Description Size
ICLR - Lu Liu 2021 - review.pdfSupporting information265.34 kB
Adobe PDF
ICLR 2021 - Lu Liu - paper.pdfAccepted version14.7 MB
Adobe PDF
Full metadata record
Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources. This problem has seen growing interest and has inspired the development of benchmarks such as Meta-Dataset. A key challenge in this multi-domain setting is to effectively integrate the feature representations from the diverse set of training domains. Here, we propose a Universal Representation Transformer (URT) layer, that meta-learns to leverage universal features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations. In experiments, we show that URT sets a new state-of-the-art result on Meta-Dataset. Specifically, it achieves top-performance on the highest number of data sources compared to competing methods. We analyze variants of URT and present a visualization of the attention score heatmaps that sheds light on how the model performs cross-domain generalization. Our code is available at https://github.com/liulu112601/URT.
Please use this identifier to cite or link to this item: