Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2024

Abstract

Even when using large multi-modal foundation models, few-shot learning is still challenging—if there is no proper inductive bias, it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end, we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes, i.e., as the forward diffusion adds noise to an image at each time-step, nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this, we propose Time-step Few-shot (TiF) learner. We train class-specific low-rank adapters for a text-conditioned DM to make up for the lost attributes, such that images can be accurately reconstructed from their noisy ones given a prompt. Hence, at a small time-step, the adapter and prompt are essentially a parameterization of only the nuanced class attributes. For a test image, we can use the parameterization to only extract the nuanced class attributes for classification. TiF learner significantly outperforms OpenCLIP and its adapters on a variety of fine-grained and customized few-shot learning tasks. Codes are in https://github.com/yue-zhongqi/tif.

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Conference (CVPR), Seattle, 2024 June 17-21

First Page

23263

Last Page

23272

Publisher

CVPR

City or Country

Seattle WA, USA

Additional URL

https://openaccess.thecvf.com/content/CVPR2024/papers/Yue_Few-shot_Learner_Parameterization_by_Diffusion_Time-steps_CVPR_2024_paper.pdf

Download

Share

COinS