Transductive Relation-Propagation With Decoupling Training for Few-Shot Learning
| Autor: | Shihao Bai, Wei Liu, Yuqing Ma, Xianglong Liu, Yue Yu, Xiao Bai, Meng Wang, Shuo Wang |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Relation (database)
Computer Networks and Communications Computer science business.industry Node (networking) Decoupling (cosmology) Machine learning computer.software_genre Computer Science Applications Discriminative model Artificial Intelligence Benchmark (computing) Feature (machine learning) Graph (abstract data type) Embedding Artificial intelligence business computer Software |
| Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 33:6652-6664 |
| ISSN: | 2162-2388 2162-237X |
| DOI: | 10.1109/tnnls.2021.3082928 |
| Popis: | Few-shot learning, aiming to learn novel concepts from one or a few labeled examples, is an interesting and very challenging problem with many practical advantages. Existing few-shot methods usually utilize data of the same classes to train the feature embedding module and in a row, which is unable to learn adapting to new tasks. Besides, traditional few-shot models fail to take advantage of the valuable relations of the support-query pairs, leading to performance degradation. In this article, we propose a transductive relation-propagation graph neural network (GNN) with a decoupling training strategy (TRPN-D) to explicitly model and propagate such relations across support-query pairs, and empower the few-shot module the ability of transferring past knowledge to new tasks via the decoupling training. Our few-shot module, namely TRPN, treats the relation of each support-query pair as a graph node, named relational node, and resorts to the known relations between support samples, including both intraclass commonality and interclass uniqueness. Through relation propagation, the model could generate the discriminative relation embeddings for support-query pairs. To the best of our knowledge, this is the first work that decouples the training of the embedding network and the few-shot graph module with different tasks, which might offer a new way to solve the few-shot learning problem. Extensive experiments conducted on several benchmark datasets demonstrate that our method can significantly outperform a variety of state-of-the-art few-shot learning methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|