Few-Shot Classification with Feature mAP Reconstruction Networks

Abstract

In this paper we reformulate few-shot classification as a reconstruction problem in latent space. The ability of the network to reconstruct a query feature map from support features of a given class predicts membership of the query in that class. We introduce a novel mechanism for few-shot classification by regressing directly from support features to query features in closed form, without introducing any new modules or large-scale learnable parameters. The resulting Feature Map Reconstruction Networks are both more performant and computationally efficient than previous approaches. We demonstrate consistent and substantial accuracy gains on four fine-grained benchmarks with varying neural architectures. Our model is also competitive on the non-fine-grained mini-ImageNet and tiered-ImageNet benchmarks with minimal bells and whistles.

Cite

Text

Wertheimer et al. "Few-Shot Classification with Feature mAP Reconstruction Networks." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00792

Markdown

[Wertheimer et al. "Few-Shot Classification with Feature mAP Reconstruction Networks." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/wertheimer2021cvpr-fewshot/) doi:10.1109/CVPR46437.2021.00792

BibTeX

@inproceedings{wertheimer2021cvpr-fewshot,
  title     = {{Few-Shot Classification with Feature mAP Reconstruction Networks}},
  author    = {Wertheimer, Davis and Tang, Luming and Hariharan, Bharath},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {8012-8021},
  doi       = {10.1109/CVPR46437.2021.00792},
  url       = {https://mlanthology.org/cvpr/2021/wertheimer2021cvpr-fewshot/}
}