D3G: Diverse Demographic Data Generation Increases Zero-Shot Image Classification Accuracy within Multimodal Models

Image classification is a task essential for machine perception to achieve human-level image understanding. Multimodal models such as CLIP have been able to perform well on this task by learning semantic similarities across vision and language; however, despite these advances, image classification is still a challenging task. Models with low capacity often suffer from underfitting and thus underperform on fine-grained image classification. Along with this, it is important to ensure high-quality data with rich cross-modal representations of each class, which is often difficult to generate. When datasets do not enforce balanced demographics, the predictions will be biased toward the more represented class, while others will be neglected. We focus on how these issues can lead to harmful bias for zero-shot image classification, and explore how to combat these issues in demographic bias. We propose Diverse Demographic Data Generation (D3G), a training-free, zero-shot method of boosting classification accuracy while reducing demographic bias in pre-trained multimodal models. With this method, we utilize CLIP as our base multimodal model and Stable Diffusion XL as our generative model. We demonstrate that providing diverse demographic data at inference time improves performance for these models, and explore the impact of individual demographics on the resulting accuracy metric.

Paper

References (10)

072022. High-resolution image synthesis with latent diffusion modelsProceedings of the IEEE/CVF conference on computer vision and pattern recognition
082023. What does a platypus look like? generating customized prompts for zero-shot image classificationProceedings of the IEEE/CVF International Conference on Computer Vision
09The base multimodal model can distinguish between similar classes. Our method will not improve performance if this is not the case
102022. Sus-x: Training-free name-only transfer of vision-language modelsarXiv

Similar papers

© 2026 NYSGPT2525 LLC