Singular Value Few-shot Adaptation of Vision-Language Models
By: Taha Koleilat, Hassan Rivaz, Yiming Xiao
Potential Business Impact:
Teaches AI to learn new things with fewer examples.
Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-grained domains remains difficult due to reliance on prompt engineering and the high cost of full model fine-tuning. Existing adaptation approaches rely on augmented components, such as prompt tokens and adapter modules, which could limit adaptation quality, destabilize the model, and compromise the rich knowledge learned during pretraining. In this work, we present \textbf{CLIP-SVD}, a novel \textit{multi-modal} and \textit{parameter-efficient} adaptation technique that leverages Singular Value Decomposition (SVD) to modify the internal parameter space of CLIP without injecting additional modules. Specifically, we fine-tune only the singular values of the CLIP parameter matrices to rescale the basis vectors for domain adaptation while retaining the pretrained model. This design enables enhanced adaptation performance using only \textbf{0.04\%} of the model's total parameters and better preservation of its generalization ability. CLIP-SVD achieves state-of-the-art classification results on 11 natural and 10 biomedical datasets, outperforming previous methods in both accuracy and generalization under few-shot settings. Additionally, we leverage a natural language-based approach to analyze the effectiveness and dynamics of the CLIP adaptation to allow interpretability of CLIP-SVD. The code is publicly available at https://github.com/HealthX-Lab/CLIP-SVD.
Similar Papers
Singular Value Few-shot Adaptation of Vision-Language Models
CV and Pattern Recognition
Teaches computers to understand new things with less data.
Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
CV and Pattern Recognition
Makes computers judge video quality better, faster.
Multiple Stochastic Prompt Tuning for Few-shot Adaptation under Extreme Domain Shift
CV and Pattern Recognition
Helps AI understand new things with few examples.