生成式分类器能避开数据偏差陷阱，提升模型鲁棒性。
Generative Classifiers Avoid Shortcut Solutions
- 用生成模型同时建模关键与虚假特征，避免依赖错误关联
- 在五个图像和文本分布偏移任务中达到顶尖性能
- 无需特殊增强或超参调优，适合医疗、遥感等真实场景
判别式分类方法常因过度依赖与标签虚假相关的特征而失效，尤其在分布发生微小变化时。这类失败源于对表面相关特征的过度依赖。我们发现，使用类别条件生成模型的生成式分类器可通过同时建模所有特征（包括核心特征和虚假特征），避免仅依赖虚假特征的问题。这类方法训练简单，无需专门的数据增强、强正则化、额外超参数，也无需预先知晓虚假相关性。实验表明，基于扩散模型和自回归的生成式分类器在五个标准图像与文本分布偏移基准上均达到当前最优表现，并显著降低真实应用中（如医学、卫星数据）虚假相关性的负面影响。最后，我们通过一个高斯简化设定分析了生成式分类器的归纳偏置，以及决定其何时优于判别式模型的数据特性。
原文摘要 · Abstract (English)
Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones. These generative classifiers are simple to train, avoiding the need for specialized augmentations, strong regularization, extra hyperparameters, or knowledge of the specific spurious correlations to avoid. We find that diffusion-based and autoregressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks and reduce the impact of spurious correlations in realistic applications, such as medical or satellite datasets. Finally, we carefully analyze a Gaussian toy setting to understand the inductive biases of generative classifiers, as well as the data properties that determine when generative classifiers outperform discriminative ones.
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。