Toward Better Generalization of Cross-Domain Few-Shot Classification in Tibetan Character With Contrastive Learning and Meta Fine-Tuning

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Few-shot classification aims to classify unseen classes (query instances) with few labeled samples from each class (support instances). However, current few-shot learning methods assume that the training and testing sets obey the same distribution. When there exists a huge domain gap between the training and testing sets, they fail to generalize well across domains. In this work, we tackle the cross-domain few-shot learning (CD-FSL) problem in Tibetan characters from two perspectives. In the meta-training phase, we seamlessly introduce contrastive learning into the episodic training paradigm and apply a data augmentation strategy to seek better feature representations thereby improving the ability to recognize unseen categories. In the meta-finetuning phase, we then integrate the above algorithm into transfer learning and propose a fine-tuning method that generates episodic synthetic query sets to enhance generalization capability across domains. These two stages force the model to overcome the domain shift between training and testing sets. Extensive experiments show that our simple approach allows us to establish competitive results on the well-known few-shot learning dataset Omniglot and state-of-the-art results on our Tibetan character datasets. The code will be publicly available in this repository: https://github.com/coder-bossin/fs-TCR.
Funding Information
  • Fundamental Research Funds for the Central University of Northwest Minzu University (31920230065, 31920220037, 31920220132)
  • Gansu Provincial Science and Technology Plan Project (22JR5RA187, 23YFGA0072)
  • National Natural Science Foundation of China (62166036, 61772430)
  • Gansu Provincial Education Technology Innovation Project (2023CXZX-176)

This publication has 39 references indexed in Scilit: