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：数据中的伪相关性（即多个线索可预测目标标签）常导致捷径学习现象，使模型依赖错误且易学的线索而忽略可靠线索。本文提出一种利用扩散概率模型（DPMs）生成合成反事实的集成多样化框架。我们发现，即使训练数据中多种视觉线索高度相关，DPMs仍具有独立表征这些线索的固有能力。我们利用这一特性促进模型多样性，并通过实证验证了该方法在多种多样化目标下的有效性。实验表明，扩散引导的多样化能使模型避免关注捷径线索，其集成多样性性能可媲美需要额外数据收集的先前方法。