Few-shot intent detection with self-supervised pretraining and prototype-aware attention

S Yang, YJ Du, X Zheng, XY Li, XL Chen, YL Li… - Pattern Recognition, 2024‏ - Elsevier
Few-shot intent detection is a more challenging application. However, traditional prototypical
networks based on averaging often suffer from issues such as missing key information, poor …

A framework for bilevel optimization on Riemannian manifolds

A Han, B Mishra, P Jawanpuria, A Takeda - arxiv preprint arxiv …, 2024‏ - arxiv.org
Bilevel optimization has gained prominence in various applications. In this study, we
introduce a framework for solving bilevel optimization problems, where the variables in both …

AMMD: Attentive maximum mean discrepancy for few-shot image classification

J Wu, S Wang, J Sun - Pattern Recognition, 2024‏ - Elsevier
Metric-based methods have attained promising performance for few-shot image
classification. Maximum Mean Discrepancy (MMD) is a typical distance between …

Classification of ground‐based auroral images by learning deep tensor feature representation on Riemannian manifold

Y Hu, Z Zhou, P Yang, X Zhao… - Journal of Geophysical …, 2024‏ - Wiley Online Library
Automatically classifying a huge amount of ground‐based auroral images is essential to
facilitate aurora morphology statistical research and aid in comprehending the …

Learning from not-all-negative pairwise data and unlabeled data

S Huang, J Li, C Hua - Pattern Recognition, 2025‏ - Elsevier
A weakly-supervised approach utilizing data pairs with comparative or similarity/dissimilarity
information has gained popularity in various fields due to its cost-effectiveness. However, the …

Riemannian Bilevel Optimization

S Dutta, X Cheng, S Sra - arxiv preprint arxiv:2405.15816, 2024‏ - arxiv.org
We develop new algorithms for Riemannian bilevel optimization. We focus in particular on
batch and stochastic gradient-based methods, with the explicit goal of avoiding second …

[HTML][HTML] Orthogonal Capsule Network with Meta-Reinforcement Learning for Small Sample Hyperspectral Image Classification

PYO Amoako, G Cao, B Shi, D Yang, BB Acka - Remote Sensing, 2025‏ - mdpi.com
Most current hyperspectral image classification (HSIC) models require a large number of
training samples, and when the sample size is small, the classification performance …

Marginal debiased network for fair visual recognition

M Wang, W Deng, J Hu, S Su - Pattern Recognition, 2025‏ - Elsevier
Deep neural networks (DNNs) are often prone to learn the spurious correlations between
target classes and bias attributes, like gender and race, inherent in a major portion of …

FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds

H Tabealhojeh, SK Roy, P Adibi… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Meta-learning problem is usually formulated as a bi-level optimization in which the task-
specific and the meta-parameters are updated in the inner and outer loops of optimization …

[PDF][PDF] EMPHASIZING DATA QUALITY FOR THE IDENTIFICATION OF CHILI VARIETIES IN THE CONTEXT OF SMART AGRICULTURE.

W Suwarningsih, R Kirana, PH Khotimah… - … Journal of Information …, 2024‏ - ijikm.org
ABSTRACT Aim/Purpose This research aims to evaluate models from meta-learning
techniques, such as Riemannian Model Agnostic Meta-Learning (RMAML), Model-Agnostic …