@article{Ye_Li_Zhan_2021, title={Task Cooperation for Semi-Supervised Few-Shot Learning}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17277}, DOI={10.1609/aaai.v35i12.17277}, abstractNote={Training a model with limited data is an essential task for machine learning and visual recognition. Few-shot learning approaches meta-learn a task-level inductive bias from SEEN class few-shot tasks, and the meta-model is expected to facilitate the few-shot learning with UNSEEN classes. Inspired by the idea that unlabeled data can be utilized to smooth the model space in traditional semi-supervised learning, we propose TAsk COoperation (TACO) which takes advantage of unsupervised tasks to smooth the meta-model space. Specifically, we couple the labeled support set in a few-shot task with easily-collected unlabeled instances, prediction agreement on which encodes the relationship between tasks. The learned smooth meta-model promotes the generalization ability on supervised UNSEEN few-shot tasks. The state-of-the-art few-shot classification results on MiniImageNet and TieredImageNet verify the superiority of TACO to leverage unlabeled data and task relationship in meta-learning.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ye, Han-Jia and Li, Xin-Chun and Zhan, De-Chuan}, year={2021}, month={May}, pages={10682-10690} }