Improving meta-learning classification with prototype enhancement

I2MEP-Net: Inter- and Intra-Modality Enhancing Prototypical Network for Few-shot Hyperspectral Image Classification

W Wang, F Liu, L Xiao - IEEE Transactions on Geoscience and …, 2024 - ieeexplore.ieee.org
Prototypical network, celebrated for its flexible network structure and metric computation
capability, has become a prevailing strategy in addressing challenges associated with few …
相关文章

Task-adaptive Few-shot Learning on Sphere Manifold

X He, F Li - 2022 26th International Conference on Pattern …, 2022 - ieeexplore.ieee.org
Few-shot learning aims to learn generalized knowledge from limited data, which is a
challenging study. Metric-based few-shot learning is the most widely studied direction, and …
相关文章 所有 2 个版本

Class-wise Attention Reinforcement for Semi-supervised Meta-Learning

X Pan, F Li - 2022 26th International Conference on Pattern …, 2022 - ieeexplore.ieee.org
Meta-learning aims to learn some common knowledge quickly from the limited labeled
examples. Semi-supervised meta-learning is developed to improve the learning …
相关文章 所有 2 个版本

Adaptive Weights and Sample's Distribution for Few Shot Classification

T Yang, F Li - 2022 IEEE International Conference on Systems …, 2022 - ieeexplore.ieee.org
In recent years, few-shot classification algorithms have been developing. But many few-shot
classification algorithms are facing their bottlenecks. After our study and research of the …
相关文章