SSL-ProtoNet: Self-supervised Learning Prototypical Networks for few-shot learning


Lim, Jit Yan and Lim, Kian Ming and Lee, Chin Poo and Tan, Yong Xuan (2024) SSL-ProtoNet: Self-supervised Learning Prototypical Networks for few-shot learning. Expert Systems with Applications, 238. p. 122173. ISSN 0957-4174

[img] Text
66.pdf - Published Version
Restricted to Repository staff only

Download (1MB)


Few-shot learning is seeking to generalize well to unseen tasks with insufficient labeled samples. Existing works have achieved generalization by exploring inter-class discrimination. However, their performance is limited because sample discrimination is neglected. In this work, we propose a metric-based few-shot approach that leverages self-supervised learning, Prototypical networks, and knowledge distillation, referred to as SSLProtoNet, to utilize sample discrimination. The proposed SSL-ProtoNet consists of three stages: pre-training stage, fine-tuning stage, and self-distillation stage. In the pre-training stage, self-supervised learning is leveraged to cluster the samples with their augmented variants to enhance the sample discrimination. The learned representation is then served as an initial point for the next stage. In the fine-tuning stage, the model weights transferred from the pre-training stage are fine-tuned to the target few-shot tasks. A self-supervised loss and a few-shot loss are integrated to prevent overfitting during few-shot task adaptation and to maintain the embedding diversity. In the self-distillation stage, the model is arranged in a teacher–student architecture. The teacher model will serve as a guidance in student model training to reduce overfitting and further improve the performance. The experimental results show that the proposed SSL-ProtoNet outshines the stateof-the-art few-shot image classification methods on three benchmark few-shot datasets, namely, miniImageNet, tieredImageNet, and CIFAR-FS. The source code for the proposed method is available at Jityan/sslprotonet.

Item Type: Article
Uncontrolled Keywords: Few-shot classification Self-supervised learning Prototypical networks Few-shot learning Knowledge distillation
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 31 Jan 2024 00:59
Last Modified: 31 Jan 2024 00:59


Downloads per month over past year

View ItemEdit (login required)