{"ID":2871331,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.11220","arxiv_id":"2509.11220","title":"ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification","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.","short_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 att...","url_abs":"https://arxiv.org/abs/2509.11220","url_pdf":"https://arxiv.org/pdf/2509.11220v1","authors":"[\"Gao Yu Lee\",\"Tanmoy Dam\",\"Md Meftahul Ferdaus\",\"Daniel Puiu Poenar\",\"Vu N. Duong\"]","published":"2025-09-14T11:44:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Convolutional Neural Network\",\"Variational Autoencoder\"]","has_code":false,"code_links":[{"ID":609849,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871331,"paper_url":"https://arxiv.org/abs/2509.11220","paper_title":"ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification","repo_url":"https://github.com/GreedYLearner1146/ANROT-HELANet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}