TY - GEN
T1 - Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
AU - Baik, Sungyong
AU - Choi, Janghoon
AU - Kim, Heewon
AU - Cho, Dohee
AU - Min, Jaesik
AU - Lee, Kyoung Mu
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the popularity as one of the representative few-shot learning methods for its flexibility and applicability to diverse problems. However, MAML and its variants often resort to a simple loss function without any auxiliary loss function or regularization terms that can help achieve better generalization. The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct. Instead of attempting to hand-design an auxiliary loss function for each application and task, we introduce a new meta-learning framework with a loss function that adapts to each task. Our proposed framework, named Meta-Learning with Task-Adaptive Loss Function (MeTAL), demonstrates the effectiveness and the flexibility across various domains, such as few-shot classification and few-shot regression.
AB - In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the popularity as one of the representative few-shot learning methods for its flexibility and applicability to diverse problems. However, MAML and its variants often resort to a simple loss function without any auxiliary loss function or regularization terms that can help achieve better generalization. The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct. Instead of attempting to hand-design an auxiliary loss function for each application and task, we introduce a new meta-learning framework with a loss function that adapts to each task. Our proposed framework, named Meta-Learning with Task-Adaptive Loss Function (MeTAL), demonstrates the effectiveness and the flexibility across various domains, such as few-shot classification and few-shot regression.
UR - http://www.scopus.com/inward/record.url?scp=85126802337&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00933
DO - 10.1109/ICCV48922.2021.00933
M3 - Conference contribution
AN - SCOPUS:85126802337
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 9445
EP - 9454
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -