Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome this issue, our study introduces Saliency Diversified Deep Ensemble (SDDE), a novel approach that promotes diversity among ensemble members by leveraging saliency maps. Through incorporating saliency map diversification, our method outperforms conventional ensemble techniques and improves calibration in multiple classification and OOD detection tasks. In particular, the proposed method achieves state-of-the-art OOD detection quality, calibration, and accuracy on multiple benchmarks, including CIFAR10/100 and large-scale ImageNet datasets.

翻译：深度集成能够在分类和分布外（OOD）检测任务中取得最先进的结果。然而，由于集成内学习模式的同质性，其有效性受到限制。为克服此问题，本研究提出了显著图多样化深度集成（SDDE），这是一种通过利用显著图来促进集成成员间多样性的新方法。通过引入显著图多样化，我们的方法超越了传统集成技术，并在多个分类和OOD检测任务中改善了校准性能。特别地，所提方法在包括CIFAR10/100和大规模ImageNet数据集在内的多个基准测试中，实现了最先进的OOD检测质量、校准性能和分类精度。