Vincent Gripon's Homepage

Research and Teaching Blog

Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification

Y. H. V. Gripon and S. Pateux, "Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification," in 25th International Conference on Pattern Recognition (ICPR), pp. 8164--8171, January 2021.

In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.

Download manuscript.

Bibtex
@inproceedings{GriPat20211,
  author = {Yuqing Hu, Vincent Gripon and Stéphane
Pateux},
  title = {Graph-based Interpolation of Feature
Vectors for Accurate Few-Shot Classification},
  booktitle = {25th International Conference on
Pattern Recognition (ICPR)},
  year = {2021},
  pages = {8164--8171},
  month = {January},
}




You are the 2092837th visitor

Vincent Gripon's Homepage