Loading...
FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation
Bai, Yunwei Tan, Ying Kiat Chen, Shiming Shu, Yao Chen, Tsuhan
Bai, Yunwei
Tan, Ying Kiat
Chen, Shiming
Shu, Yao
Chen, Tsuhan
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Few-shot learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (support set) as reference. So far, plenty of algorithms involve training data augmentation to improve the generalization capability of FSL models, but outlier queries or support images during inference can still pose great generalization challenges. In this work, to reduce the bias caused by the outlier samples, we generate additional test-class samples by combining original samples with suitable train-class samples via a generative image combiner. Then, we obtain averaged features via an augmentor, which leads to more typical representations through the averaging. We experimentally and theoretically demonstrate the effectiveness of our method, obtaining a test accuracy improvement proportion of around 10% (e.g., from 46.86% to 53.28%) for trained FSL models. Importantly, given a pretrained image combiner, our method is training-free for off-the-shelf FSL models, whose performance can be improved without extra datasets nor further training of the models themselves.
Citation
Y. Bai, Y. K. Tan, S. Chen, Y. Shu, and T. Chen, “FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 15, pp. 15462–15471, Apr. 2025, doi: 10.1609/AAAI.V39I15.33697.
Source
Proceedings of the AAAI Conference on Artificial Intelligence
Conference
39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
Keywords
Data augmentation, Generalisation, Generalization capability, Image query, Learning models, Original sample, Outlier samples, Test accuracy, Test time, Training data
Subjects
Source
39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
Publisher
Association for the Advancement of Artificial Intelligence