# ProtoN: Prototype Node Graph Neural Network for Unconstrained Multi-Impression Ear Recognition

arXiv: https://arxiv.org/abs/2508.04381 · HTML: https://mlsanity.com/paper/2508.04381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 38 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Rethinking pooling in graph neural networks](https://mlsanity.com/paper/2010.11418/) (2020)
- [On Episodes, Prototypical Networks, and Few-shot Learning](https://mlsanity.com/paper/2012.09831/) (2020)
- [Ear Recognition: More Than a Survey](https://mlsanity.com/paper/1611.06203/) (2016)
- [Domain Adaptation for Ear Recognition Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1803.07801/) (2018)
- [The Unconstrained Ear Recognition Challenge 2019 - ArXiv Version With Appendix](https://mlsanity.com/paper/1903.04143/) (2019)
- [The Unconstrained Ear Recognition Challenge](https://mlsanity.com/paper/1708.06997/) (2017)
- [Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild](https://mlsanity.com/paper/1711.09952/) (2017)
- [Hierarchical Meta Learning](https://mlsanity.com/paper/1904.09081/) (2019)

## Abstract (arXiv)

Ear biometrics offer a stable and contactless modality for identity recognition, yet their effectiveness remains limited by the scarcity of annotated data and significant intra-class variability. Existing methods typically extract identity features from individual impressions in isolation, restricting their ability to capture consistent and discriminative representations. To overcome these limitations, a few-shot learning framework, ProtoN, is proposed to jointly process multiple impressions of an identity using a graph-based approach. Each impression is represented as a node in a class-specific graph, alongside a learnable prototype node that encodes identity-level information. This graph is processed by a Prototype Graph Neural Network (PGNN) layer, specifically designed to refine both impression and prototype representations through a dual-path message-passing mechanism. To further enhance discriminative power, the PGNN incorporates a cross-graph prototype alignment strategy that improves class separability by enforcing intra-class compactness while maintaining inter-class distinction. Additionally, a hybrid loss function is employed to balance episodic and global classification objectives, thereby improving the overall structure of the embedding space. Extensive experiments on five benchmark ear datasets demonstrate that ProtoN achieves state-of-the-art performance, with Rank-1 identification accuracy of up to 99.60% and an Equal Error Rate (EER) as low as 0.025, showing the effectiveness for few-shot ear recognition under limited data conditions.