Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
CoRR(2024)
摘要
We propose a method for generating spurious features by leveraging
large-scale text-to-image diffusion models. Although the previous work detects
spurious features in a large-scale dataset like ImageNet and introduces
Spurious ImageNet, we found that not all spurious images are spurious across
different classifiers. Although spurious images help measure the reliance of a
classifier, filtering many images from the Internet to find more spurious
features is time-consuming. To this end, we utilize an existing approach of
personalizing large-scale text-to-image diffusion models with available
discovered spurious images and propose a new spurious feature similarity loss
based on neural features of an adversarially robust model. Precisely, we
fine-tune Stable Diffusion with several reference images from Spurious ImageNet
with a modified objective incorporating the proposed spurious-feature
similarity loss. Experiment results show that our method can generate spurious
images that are consistently spurious across different classifiers. Moreover,
the generated spurious images are visually similar to reference images from
Spurious ImageNet.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要