Bilevel Direction Preserving for Few-Shot Open-Set Recognition

Zihui Zhang, Chenghao Xu, Jiexi Yan, Cheng Deng

Abstract

Few-shot open-set recognition (FSOSR) poses a significant challenge as it requires identifying unknown classes while maintaining the classification performance of known classes, despite having limited access to labeled training samples. Current methods often employ non-directional metric-based losses to encapsulate feature attributes within the embedding space, inadvertently disregarding the potential influence of spatial distribution deviations of feature representations on open-set recognition performance. To address this, we present a novel directional metric-based method termed Bilevel Direction Preserving (BiDirP). This method incorporates two direction-preserving regularizers operating at distinct levels, specifically at the instance and prototype levels. The combined application of these two direction-preserving regularizers effectively enhances the spatial separation between prototypes of different classes and refines the classification decision boundaries, which results in an improved discriminative ability to differentiate unknown classes within a broader open space. Comprehensive experiments on public benchmarks show that BiDirP can significantly improve the detection ability of unknown classes while correctly classifying known classes.
BibTeX
@article{zhang2025bilevel,
  author = {Zihui Zhang and Chenghao Xu and Jiexi Yan and Cheng Deng},
  title = {{Bilevel Direction Preserving for Few-Shot Open-Set Recognition}},
  journal = {IEEE Trans. Multimedia},
  year = {2025},
  url = {https://openreview.net/forum?id=kwTgq9CyUL},
}

Loading related content...

Figure