Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Gao Yu, Dam, Tanmoy, Ferdaus, Md Meftahul, Poenar, Daniel Puiu, Duong, Vu N.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.11220
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909786767884288
author Lee, Gao Yu
Dam, Tanmoy
Ferdaus, Md Meftahul
Poenar, Daniel Puiu
Duong, Vu N.
author_facet Lee, Gao Yu
Dam, Tanmoy
Ferdaus, Md Meftahul
Poenar, Daniel Puiu
Duong, Vu N.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11220
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification
Lee, Gao Yu
Dam, Tanmoy
Ferdaus, Md Meftahul
Poenar, Daniel Puiu
Duong, Vu N.
Computer Vision and Pattern Recognition
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.
title ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.11220