Deep ensembles achieved state-of-the-art results in classification and out-of-distribution (OOD) detection; however, their effectiveness remains limited due to the homogeneity of learned patterns within the ensemble. To overcome this challenge, our study introduces a novel approach that promotes diversity among ensemble members by leveraging saliency maps. By incorporating saliency map diversification, our method outperforms conventional ensemble techniques in multiple classification and OOD detection tasks, while also improving calibration. Experiments on well-established OpenOOD benchmarks highlight the potential of our method in practical applications.

翻译：深度集成在分类和分布外（OOD）检测任务中取得了当前最佳成果，然而由于集成内部学习模式的高度同质性，其有效性仍受到限制。为突破这一挑战，本研究提出了一种创新方法，通过利用显著性图促进集成成员间的多样性。通过引入显著性图多样化策略，我们的方法在多项分类和OOD检测任务中均优于传统集成技术，同时改善了模型校准性能。基于权威OpenOOD基准的系列实验充分验证了该方法在实际应用中的潜力。