ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification

2025-09-14

AI Summary

To address the poor robustness of KL-divergence-based Bayesian methods in few-shot learning (FSL) against adversarial attacks and natural noise, this paper proposes a Hellinger-distance-based robust feature aggregation network. Methodologically, it introduces the Hellinger distance—novelly applied to both feature aggregation and similarity modeling—and designs a Hellinger contrastive loss, integrated with attention mechanisms, variational inference, and adversarial training. The framework simultaneously achieves strong robustness under ε=0.30 ℓ∞-bounded adversarial perturbations and σ=0.30 Gaussian noise. On miniImageNet, it improves 1-shot and 5-shot classification accuracy by 1.20% and 1.40%, respectively; attains a Fréchet Inception Distance (FID) of 2.75—significantly outperforming VAE and WAE baselines—and establishes new state-of-the-art performance across four standard FSL benchmarks.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Few-Shot Learning (FSL), which involves learning to generalize using only a few data samples, has demonstrated promising and superior performances to ordinary CNN methods. While Bayesian based estimation approaches using Kullback-Leibler (KL) divergence have shown improvements, they remain vulnerable to adversarial attacks and natural noises. We introduce ANROT-HELANet, an Adversarially and Naturally RObusT Hellinger Aggregation Network that significantly advances the state-of-the-art in FSL robustness and performance. Our approach implements an adversarially and naturally robust Hellinger distance-based feature class aggregation scheme, demonstrating resilience to adversarial perturbations up to $ε=0.30$ and Gaussian noise up to $σ=0.30$. The network achieves substantial improvements across benchmark datasets, including gains of 1.20% and 1.40% for 1-shot and 5-shot scenarios on miniImageNet respectively. We introduce a novel Hellinger Similarity contrastive loss function that generalizes cosine similarity contrastive loss for variational few-shot inference scenarios. Our approach also achieves superior image reconstruction quality with a FID score of 2.75, outperforming traditional VAE (3.43) and WAE (3.38) approaches. Extensive experiments conducted on four few-shot benchmarked datasets verify that ANROT-HELANet's combination of Hellinger distance-based feature aggregation, attention mechanisms, and our novel loss function establishes new state-of-the-art performance while maintaining robustness against both adversarial and natural perturbations. Our code repository will be available at https://github.com/GreedYLearner1146/ANROT-HELANet/tree/main.

Problem

• Enhancing few-shot learning robustness against adversarial attacks
• Improving resilience to natural noise in few-shot classification
• Advancing feature aggregation using Hellinger distance metrics

Innovation

• Hellinger distance-based feature aggregation
• Hellinger Similarity contrastive loss function
• Attention mechanisms for robust classification