Focusing Image Generation to Mitigate Spurious Correlations
원문 초록
Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in erroneous classification outcomes. In this paper, we propose a data augmentation method called Spurious Correlations Guided Synthesis (SCGS) that mitigates spurious correlations through image generation model. This approach does not require expensive spurious attribute (group) labels for the training data and can be widely applied to other debiasing methods. Specifically, SCGS first identifies the incorrect attention regions of a pre-trained classifier on the training images, and then uses an image generation model to generate new training data based on these incorrect attended regions. SCGS increases the diversity and scale of the dataset to reduce the impact of spurious correlations on classifiers. Changes in the classifier's attention regions and experimental results on three different domain datasets demonstrate that this method is effective in reducing the classifier's reliance on spurious correlations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images
Synthesizing Reality: Leveraging the Generative AI-Powered Platform Midjourney for Construction Worker Detection
Evaluating Attribute Confusion in Fashion Text-to-Image Generation
AdaptaGen: Domain-Specific Image Generation through Hierarchical Semantic Optimization Framework
HybridQ: Hybrid Classical-Quantum Generative Adversarial Network for Skin Disease Image Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.