Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs). We discover that DPMs have the inherent capability to represent multiple visual cues independently, even when they are largely correlated in the training data. We leverage this characteristic to encourage model diversity and empirically show the efficacy of the approach with respect to several diversification objectives. We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.

翻译：数据中的虚假相关性（即多种线索均能预测目标标签）常引发捷径学习现象，导致模型可能依赖错误且易学习的线索，而忽略可靠的线索。本文提出一种利用扩散概率模型生成合成反事实样本的集成多样化框架。我们发现，即使训练数据中多种视觉线索高度相关，扩散概率模型仍具有独立表征这些线索的内在能力。我们利用这一特性促进模型多样性，并通过实验验证了该方法在若干多样化目标下的有效性。研究表明，扩散引导的多样化能使模型避免关注捷径线索，其集成多样性表现可媲美需要额外数据收集的先前方法。