Improving few-shot learning by spatially-aware matching and crosstransformer
Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scale and location mismatch between objects, as only few samples from target classes are provid...
| Main Authors: | , , |
|---|---|
| 格式: | Conference item |
| 語言: | English |
| 出版: |
Springer
2023
|