Adaptive Poincaré Point to Set Distance for Few-Shot Classification


  • Rongkai Ma Monash University
  • Pengfei Fang The Australian National University Data61-CSIRO
  • Tom Drummond The University of Melbourne
  • Mehrtash Harandi Monash University Data61-CSIRO



Computer Vision (CV)


Learning and generalizing from limited examples, i.e., few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learning is to realize an embedding where samples from different classes are distinctive. Recent studies suggest that embedding via hyperbolic geometry enjoys low distortion for hierarchical and structured data, making it suitable for few-shot learning. In this paper, we propose to learn a context-aware hyperbolic metric to characterize the distance between a point and a set associated with a learned set to set distance. To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively, based on the constellation of the points. This not only makes the metric local but also dependent on the task in hand, meaning that the metric will adapt depending on the samples that it compares. We empirically show that such metric yields robustness in the presence of outliers and achieves a tangible improvement over baseline models. This includes the state-of-the-art results on five popular few-shot classification benchmarks, namely mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds-200-2011(CUB), CIFAR-FS, and FC100.




How to Cite

Ma, R., Fang, P., Drummond, T., & Harandi, M. (2022). Adaptive Poincaré Point to Set Distance for Few-Shot Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 1926-1934.



AAAI Technical Track on Computer Vision II