Few-Shot Image Classification: Just Use a Library of Pre-Trained Feature Extractors and a Simple Classifier

Abstract

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms.

Cite

Text

Chowdhury et al. "Few-Shot Image Classification: Just Use a Library of Pre-Trained Feature Extractors and a Simple Classifier." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00931

Markdown

[Chowdhury et al. "Few-Shot Image Classification: Just Use a Library of Pre-Trained Feature Extractors and a Simple Classifier." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/chowdhury2021iccv-fewshot/) doi:10.1109/ICCV48922.2021.00931

BibTeX

@inproceedings{chowdhury2021iccv-fewshot,
  title     = {{Few-Shot Image Classification: Just Use a Library of Pre-Trained Feature Extractors and a Simple Classifier}},
  author    = {Chowdhury, Arkabandhu and Jiang, Mingchao and Chaudhuri, Swarat and Jermaine, Chris},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {9445-9454},
  doi       = {10.1109/ICCV48922.2021.00931},
  url       = {https://mlanthology.org/iccv/2021/chowdhury2021iccv-fewshot/}
}