In-use calibration: improving domain-specific fine-grained few-shot recognition
M Li, H Yao - Neural Computing and Applications, 2024 - Springer
Learning to recognize novel visual classes from few samples is challenging but promising.
Previous studies have shown that few-shot model tends to overfit and lead to poor …
Previous studies have shown that few-shot model tends to overfit and lead to poor …
Enhancing Few-shot Image Classification with a Multi-faceted Self-supervised and Contrastive Learning Approach
L Hu, W Wu - IEEE Access, 2024 - ieeexplore.ieee.org
One effective approach for solving few-shot classification is learning deep representations
that measure the similarity between query images and a few support images of specific …
that measure the similarity between query images and a few support images of specific …
EFLLD-NET: Enhancing Few-Shot Learning with Local Descriptors
G Lu, W Du, F Li - International Conference on Pattern Recognition, 2025 - Springer
Few-shot image classification aims to learn a model to correctly classify images with a few
labeled data, however, feature extractors often fail to extract more generalized and …
labeled data, however, feature extractors often fail to extract more generalized and …