Year: 2024
Type: conference-paper
Abstract: Few-shot learning (FSL) usually trains models on data from one set of classes, but tests them on data from a different set of classes, providing a few labeled support samples of the unseen classes as a reference for the trained model. Due to the lack of target-relevant training data, there is usually high generalization error with respect to the test classes. In this work, we conduct empirical explorations and propose an ensemble method (namely QuickBoost), which is efficient and effective for improving the generalization of FSL. Specifically, QuickBoost includes an alternative-architecture pretrained encoder with a one-vs-all binary classifier (namely FSL-Forest) based on random forest algorithm, and is ensembled with the off-the-shelf FSL models via logit-level averaging. Experiments on three benchmarks demonstrate that our method achieves state-of-the-art performance with good efficiency. Codes are available at https://github.com/WendyBaiYunwei/FSL-QuickBoost.
Authors: Yunwei Bai, Bill Yang Cai, Ying Kiat Tan, Zangwei Zheng, Shiming Chen, Tsuhan Chen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G1795493338
OpenAlex ID: W4403780876