Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification

no code implementations • 13 Mar 2024 • Long Lan, Fengxiang Wang, Shuyan Li, Xiangtao Zheng, Zengmao Wang, Xinwang Liu

Directly fine-tuning VLMs for RS-FGSC often encounters the challenge of overfitting the seen classes, resulting in suboptimal generalization to unseen classes, which highlights the difficulty in differentiating complex backgrounds and capturing distinct ship features.

Language Modelling Zero-Shot Learning