# Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors

arXiv: https://arxiv.org/abs/2005.11450 · HTML: https://mlsanity.com/paper/2005.11450/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2020.

## Built on by (most cited first, 3 of 3)

- [Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling](https://mlsanity.com/paper/2104.04323/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning](https://mlsanity.com/paper/2108.00954/) (2021)

## Abstract (arXiv)

Prototypical networks have been shown to perform well at few-shot learning tasks in computer vision. Yet these networks struggle when classes are very similar to each other (fine-grain classification) and currently have no way of taking into account prior knowledge (through the use of tabular data). Using a spherical latent space to encode prototypes, we can achieve few-shot fine-grain classification by maximally separating the classes while incorporating domain knowledge as informative priors. We describe how to construct a hypersphere of prototypes that embed a-priori domain information, and demonstrate the effectiveness of the approach on challenging benchmark datasets for fine-grain classification, with top results for one-shot classification and 5x speedups in training time.