Department of Computer Engineering, Chosun University, Gwangju 61452, Korea.
Sensors (Basel). 2022 Aug 29;22(17):6516. doi: 10.3390/s22176516.
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model's layer response and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single-weight values, which may lead to an over-generalized saliency map. To address this issue, we use a global guidance map to rectify the weighted aggregation operation during saliency estimation, where resultant interpretations are comparatively cleaner and instance-specific. We obtain the global guidance map by performing elementwise multiplication between the feature maps and their corresponding gradient maps. To validate our study, we compare the proposed study with nine different saliency visualizers. In addition, we use seven commonly used evaluation metrics for quantitative comparison. The proposed scheme achieves significant improvement over the test images from the ImageNet, MS-COCO 14, and PASCAL VOC 2012 datasets.
类激活图 (CAM) 有助于构建显著图，以辅助解释深度神经网络的预测。基于梯度的方法通常比其他视觉可解释性分支更快，并且不需要人为指导。CAM 类研究的性能取决于主导模型的层响应和梯度的影响。典型的基于梯度的 CAM 研究依赖于加权聚合来通过将梯度图投影到单个权重值来估计显著图，这可能导致显著图过度泛化。为了解决这个问题，我们在显著图估计过程中使用全局指导图来纠正加权聚合操作，从而得到更干净和特定于实例的解释。我们通过对特征图与其相应的梯度图进行逐元素乘法来获得全局指导图。为了验证我们的研究，我们将提出的研究与九种不同的显著可视化工具进行了比较。此外，我们还使用了七种常用的评估指标进行定量比较。该方案在来自 ImageNet、MS-COCO 14 和 PASCAL VOC 2012 数据集的测试图像上取得了显著的改进。
