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

arXiv:2403.08271v1 Announce Type: new
Abstract: Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification methods. Recent advancements in large pre-trained Vision-Language Models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, particularly in understanding image content. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories, which holds considerable …

abstract arxiv availability challenge classification cs.ai cs.cv data fine-grained language language model language models prompt prompt tuning sensing ship type vision vision-language models vlms