ProtoN: Prototype Node Graph Neural Network for Unconstrained Multi-Impression Ear Recognition
This addresses the problem of reliable identity recognition in biometrics for security applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of ear biometric recognition under limited annotated data and high intra-class variability by proposing ProtoN, a few-shot learning framework that jointly processes multiple impressions using a graph-based approach with a learnable prototype node, achieving state-of-the-art performance with up to 99.60% Rank-1 accuracy and an EER as low as 0.025 on benchmark datasets.
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.