CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts

1 code implementation • 28 Nov 2023 • Yichao Cai, Yuhang Liu, Zhen Zhang, Javen Qinfeng Shi

To address this limitation, we adopt a causal generative perspective for multimodal data and propose contrastive learning with data augmentation to disentangle content features from the original representations.

Contrastive Learning Image Augmentation +1