SeGDP: Source-free Cross-domain Few-shot Learning via Semantic Guided Diversity Prompting

Source-free cross-domain few-shot learning (SF-CDFSL) aims to transfer pretrained models to target domains with minimal samples, eliminating the need for source domain data. However, limited samples constrain visual diversity and cross-domain images lack inherent semantic context or prior knowledge, impairing the feature discriminability and generalization of large-scale pretrained models, affecting transfer performance. To tackle these problems, this paper introduces Semantic Guided Diversity Prompting (SeGDP), a method that utilizes semantic guided visual prompts to enhance input diversity. Specifically, SeGDP obtains additional diversity features by concatenating different visual prompts to each support sample, guided by randomly combined and sampled text descriptions during training. Additionally, deep prompt tuning and adapter are introduced to learn static knowledge and further enhance the model's cross-domain adaptation capability. Extensive experimental results across multiple benchmarks demonstrate that the proposed SeGDP achieves state-of-the-art (SOTA) performance under SF-CDFSL task, and rivals the performance of leading source-utilized models. Our code is available on https://github.com/qwzlh/TOMM_submission.