A unified transductive and inductive learning framework for Few-Shot Learning using Graph Neural Networks
Authors:
- Jie ChangJCJie Chang
- Haodong RenHRHaodong Ren
- Zuoyong LiZLZuoyong Li
- Yinlong XuYXYinlong Xu
- Taotao LaiTLTaotao Lai
- 2 March 2025
- journal article
- Published by Elsevier in Applied Soft Computing
- Vol. 173
Abstract
No abstract availableFunding Information
- Natural Science Research of Jiangsu Higher Education Institutions of China (2108085MF205)
- Natural Science Foundation of Anhui Province (2024J02029, 2024J01209)
- National Natural Science Foundation of China (62172197, 62471207)
This publication has 20 references indexed in Scilit:
- LGLNN: Label Guided Graph Learning-Neural Network for few-shot learningNeural Networks, 2022
- Mutual CRF-GNN for Few-shot Learning2021
- DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers2020
- Adversarial Feature Hallucination Networks for Few-Shot Learning2020
- Edge-Labeling Graph Neural Network for Few-Shot Learning2019
- CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition2018
- Deep Residual Learning for Image Recognition2016
- Filter-Based Mean-Field Inference for Random Fields with Higher-Order Terms and Product Label-SpacesInternational Journal of Computer Vision, 2014
- ImageNet: A large-scale hierarchical image database2009
- Theory of continuum percolation. II. Mean field theoryPhysical Review E, 1996