Localized Latent Updates for Fine-Tuning Vision-Language Models
This addresses the need for fast and non-destructive fine-tuning in vision-language models, which is incremental as it builds on existing adapter methods.
The paper tackles the problem of fine-tuning vision-language models like CLIP efficiently without losing generalization, by proposing a lightweight adapter that updates predictions near seen datapoints, achieving results comparable to or improving on state-of-the-art in few-shot learning.
Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is desirable that updating the model is fast and that the model does not lose its capabilities on data outside of the dataset, as is often the case with classical fine-tuning approaches. In this work we suggest a lightweight adapter, that only updates the models predictions close to seen datapoints. We demonstrate the effectiveness and speed of this relatively simple approach in the context of few-shot learning, where our results both on classes seen and unseen during training are comparable with or improve on the state of the art.