Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
This addresses the issue of improving ensemble reliability for tasks like classification and OOD detection, though it appears incremental as it builds on existing ensemble methods with a novel diversification technique.
The paper tackled the problem of limited effectiveness in deep ensembles due to homogeneity by introducing Saliency Diversified Deep Ensemble (SDDE), which uses saliency maps to promote diversity, resulting in state-of-the-art performance in OOD detection, calibration, and accuracy on benchmarks like CIFAR10/100 and ImageNet.
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.