TY - GEN
T1 - Adaptive Anchor Label Propagation for Transductive Few-Shot Learning
AU - Lazarou, Michalis
AU - Avrithis, Yannis
AU - Ren, Guangyu
AU - Stathaki, Tania
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Few-shot learning addresses the issue of classifying images using limited labeled data. Exploiting unlabeled data through the use of transductive inference methods such as label propagation has been shown to improve the performance of few-shot learning significantly. Label propagation infers pseudo-labels for unlabeled data by utilizing a constructed graph that exploits the underlying manifold structure of the data. However, a limitation of the existing label propagation approaches is that the positions of all data points are fixed and might be sub-optimal so that the algorithm is not as effective as possible. In this work, we propose a novel algorithm that adapts the feature embeddings of the labeled data by minimizing a differentiable loss function optimizing their positions in the manifold in the process. Our novel algorithm, Adaptive Anchor Label Propagation, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively. We provide experimental results highlighting the merits of our algorithm on four widely used few-shot benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS and two commonly used backbones, ResNet12 and WideResNet-28-10. The source code can be found at https://github.com/MichalisLazarou/A2LP.
AB - Few-shot learning addresses the issue of classifying images using limited labeled data. Exploiting unlabeled data through the use of transductive inference methods such as label propagation has been shown to improve the performance of few-shot learning significantly. Label propagation infers pseudo-labels for unlabeled data by utilizing a constructed graph that exploits the underlying manifold structure of the data. However, a limitation of the existing label propagation approaches is that the positions of all data points are fixed and might be sub-optimal so that the algorithm is not as effective as possible. In this work, we propose a novel algorithm that adapts the feature embeddings of the labeled data by minimizing a differentiable loss function optimizing their positions in the manifold in the process. Our novel algorithm, Adaptive Anchor Label Propagation, outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively. We provide experimental results highlighting the merits of our algorithm on four widely used few-shot benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS and two commonly used backbones, ResNet12 and WideResNet-28-10. The source code can be found at https://github.com/MichalisLazarou/A2LP.
KW - few-shot learning
KW - label propagation
KW - transductive inference
UR - http://www.scopus.com/inward/record.url?scp=85180778499&partnerID=8YFLogxK
U2 - 10.1109/ICIP49359.2023.10223033
DO - 10.1109/ICIP49359.2023.10223033
M3 - Conference Proceeding
AN - SCOPUS:85180778499
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 331
EP - 335
BT - 2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings
PB - IEEE Computer Society
T2 - 30th IEEE International Conference on Image Processing, ICIP 2023
Y2 - 8 October 2023 through 11 October 2023
ER -