# Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation Source: [Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:57:04.379Z Authors: AprilPyone MaungMaung, Huy H. Nguyen, Hitoshi Kiya, Isao Echizen Published: 2024-02-13T03:55:09.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()