Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Text-Guided Multi-Scale Frequency Representation Adaptation

About

Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods have shown promising results, they exhibit notable limitations. First, most existing methods operate in the signal space domain, which results in substantial information redundancy. Second, most existing methods utilize fixed prompts or adaptation layers, failing to fully account for the multi-scale characteristics of signals. To address these challenges, we propose the Multi-Scale Frequency Adapter (FreqAdapter), which integrates textual information and performs multi-scale fine-tuning of signals in the frequency domain. Additionally, we introduce a multi-scale adaptation strategy to optimize receptive fields across different frequency ranges, further enhancing the model's representational capacity. Extensive experiments on multimodal models, including CLIP and LLaVA, demonstrate that FreqAdapter significantly improves both performance and efficiency. FreqAdapter improves performance with minimal cost and fast convergence within one epoch. Code is available at https://github.com/Kelvin-ywc/FreqAdapter.

Weicai Yan, Xinhua Ma, Wang Lin, Tao Jin• 2026

Related benchmarks

TaskDatasetResultRank
Text-to-Image RetrievalFlickr30k (test)
Recall@178.58
525
Image-to-Text RetrievalFlickr30k (test)
R@190.5
472
Image-to-Text RetrievalFlickr30k (val)
Recall@190.9
70
Text-to-Image RetrievalFlickr30k (val)
R@177.6
70
Text-to-Image RetrievalCOCO 2017
Recall@570.92
43
Image-to-Text RetrievalCOCO 2017
R@161.42
19
Showing 6 of 6 rows

Other info

Follow for update