用生成模型发现并可视化细微差异，帮助人类区分难辨类别
Teaching Humans Subtle Differences with DIFFusion
- 通过生成反事实图像，精准展现类间微小差异
- 仅需少量数据即可实现准确转换，跨领域表现稳定
- 适合科学教育与细粒度分类研究，提升人类识别能力
科学判断常需识别难以言说的细微视觉差异。我们提出一种系统，利用生成模型自动发现并可视化类别间的最小判别特征，同时保持个体身份一致。该方法生成具有针对性的微小变换图像，在数据稀疏、样本无配对、类别边界无法描述的场景下仍表现良好。在黑洞模拟、蝴蝶分类和医学影像等六个领域中，仅用少量训练数据即实现精确过渡，揭示了已有判别特征和新发现的细微差异，显著提升分类区分度。用户研究表明，生成的反事实图像在教学人类区分细粒度类别方面明显优于传统方法，展示了生成模型推动视觉学习与科学研究的潜力。
原文摘要 · Abstract (English)
Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal discriminative features between categories while preserving instance identity. Our method generates counterfactual visualizations with subtle, targeted transformations between classes, performing well even in domains where data is sparse, examples are unpaired, and category boundaries resist verbal description. Experiments across six domains, including black hole simulations, butterfly taxonomy, and medical imaging, demonstrate accurate transitions with limited training data, highlighting both established discriminative features and novel subtle distinctions that measurably improved category differentiation. User studies confirm our generated counterfactuals significantly outperform traditional approaches in teaching humans to correctly differentiate between fine-grained classes, showing the potential of generative models to advance visual learning and scientific research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。