Adapting Vision Transformer for Few-Shot Remote Sensing Image Segmentation: Synergizing In-Domain Representations And Pretrained Model Guidance
T Gao, Z Gao - … 2024-2024 IEEE International Geoscience and …, 2024 - ieeexplore.ieee.org
Deep neural networks, especially Transformers, struggle with generalizing to objects of
unseen categories under conditions of data scarcity. In this work, we adapt a plain Vision …
unseen categories under conditions of data scarcity. In this work, we adapt a plain Vision …