Affiliation:
1. School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, China
2. Beijing Institute of Technology Chongqing Center for Microelectronics and Microsystems, Chongqing 401332, China
3. Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing 314019, China
Abstract
Zero-shot learning (ZSL) is implemented by transferring knowledge from seen classes to unseen classes through embedding space or feature generation. However, the embedding-based method has a hubness problem, and the generation-based method may contain considerable bias. To solve these problems, a joint model with multiple generative adversarial networks (JG-ZSL) is proposed in this paper. Firstly, we combined the generation-based model and the embedding-based model to build a hybrid ZSL framework by mapping the real samples and the synthetic samples into the embedding space for classification, which alleviates the problem of data imbalance effectively. Secondly, based on the original generation-method model, a coupled GAN is introduced to generate semantic embeddings, which can generate semantic vectors for unseen classes in embedded space to alleviate the bias of mapping results. Finally, semantic-relevant self-adaptive margin center loss was used, which can explicitly encourage intra-class compactness and inter-class separability, and it can also guide coupled GAN to generate discriminative and representative semantic features. All the experiments on the four standard datasets (CUB, AWA1, AWA2, SUN) show that the proposed method is effective.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference52 articles.
1. El Mrabet, M.A., El Makkaoui, K., and Faize, A. (2021, January 3–5). Supervised Machine Learning: A Survey. Proceedings of the 2021 4th International Conference on Advanced Communication Technologies and Networking (CommNet), Rabat, Morocco.
2. Tyukin, I.Y., Gorban, A.N., Alkhudaydi, M.H., and Zhou, Q. (2021, January 18–22). Demystification of Few-shot and One-shot Learning. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.
3. Jiao, Q., Liu, Z., Li, G., Ye, L., and Wang, Y. (2020, January 6–10). Fine-Grained Image Classification with Coarse and Fine Labels on One-Shot Learning. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), London, UK.
4. Generalizing from a Few Examples: A Survey on Few-Shot Learning;Wang;Assoc. Comput. Mach.,2021
5. Toward open set recognition;Scheirer;IEEE Trans. Pattern Anal. Mach. Intell.,2013
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献