A Universal Representation Transformer Layer for Few-Shot Image Classification
- Publication Type:
- Journal Article
- Citation:
- 2020
- Issue Date:
- 2020-06-21
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
ICLR - Lu Liu 2021 - review.pdf | Supporting information | 265.34 kB | |||
ICLR 2021 - Lu Liu - paper.pdf | Accepted version | 14.7 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
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: