Few-Shot Attribute Learning

Mengye Ren, Eleni Triantafillou, Kuan-Chieh Wang, James Lucas, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard ZemelICLR 2022 · OpenReview

Abstract

Semantic concepts are often defined by a combination of attributes. The use of attributes also facilitates learning of new concepts with zero or few examples. However, the zero-shot learning paradigm assumes that the set of attributes are known and fixed, which is a limitation if a test-time task depends on a previously irrelevant attribute. In this work we study rapid learning of attributes that are previously not labeled in the dataset. Compared to standard few-shot learning of semantic classes, learning new attributes imposes a stiffer challenge. We found that directly supervising the model with a set of training attributes does not generalize well on the test attributes, whereas self-supervised pre-training brings significant improvement. We further experimented with random splits of the attribute space and found that the predictability of attributes provides an informative estimate of a model's ability to generalize.
BibTeX
@inproceedings{ren2022few,
  author = {Mengye Ren and Eleni Triantafillou and Kuan-Chieh Wang and James Lucas and Jake Snell and Xaq Pitkow and Andreas S. Tolias and Richard Zemel},
  title = {{Few-Shot Attribute Learning}},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
  url = {https://openreview.net/forum?id=qCBmozgVr9r},
}

Loading related content...

Figure