Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concerns about model transparency and biases persist. Explainable methods are viewed as the solution to address these challenges. In this study, we introduce the Occlusion Sensitivity Analysis with Deep Feature Augmentation Subspace (OSA-DAS), a novel perturbation-based interpretability approach for computer vision. While traditional perturbation methods make only use of occlusions to explain the model predictions, OSA-DAS extends standard occlusion sensitivity analysis by enabling the integration with diverse image augmentations. Distinctly, our method utilizes the output vector of a DNN to build low-dimensional subspaces within the deep feature vector space, offering a more precise explanation of the model prediction. The structural similarity between these subspaces encompasses the influence of diverse augmentations and occlusions. We test extensively on the ImageNet-1k, and our class- and model-agnostic approach outperforms commonly used interpreters, setting it apart in the realm of explainable AI.

通过引入基于OSA-DAS的深度特征增强子空间的遮挡敏感性分析，针对计算机视觉领域，本研究提出了一种新型的基于扰动的可解释性方法，以更准确地解释模型预测结果，通过对DNN的输出向量构建低维子空间，利用不同图像增强和遮挡的影响来实现，经广泛测试后，在ImageNet-1k数据集上，我们的方法在解释人工智能领域中表现出色，超越了常用的解释器。

深度特征空间中的增强子空间扰动下的遮挡敏感性分析