Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly for self-supervised models. Most existing methods for generating saliency maps rely on ground truth labels, restricting their use to supervised tasks. EigenCAM is the only notable label-independent alternative, leveraging Singular Value Decomposition to generate saliency maps applicable across CNN models, but it does not fully exploit the tensorial structure of feature maps. In this work, we introduce the Tucker Saliency Map (TSM) method, which applies Tucker tensor decomposition to better capture the inherent structure of feature maps, producing more accurate singular vectors and values. These are used to generate high-fidelity saliency maps, effectively highlighting objects of interest in the input. We further extend EigenCAM and TSM into multivector variants -Multivec-EigenCAM and Multivector Tucker Saliency Maps (MTSM)- which utilize all singular vectors and values, further improving saliency map quality. Quantitative evaluations on supervised classification models demonstrate that TSM, Multivec-EigenCAM, and MTSM achieve competitive performance with label-dependent methods. Moreover, TSM enhances explainability by approximately 50% over EigenCAM for both supervised and self-supervised models. Multivec-EigenCAM and MTSM further advance state-of-the-art explainability performance on self-supervised models, with MTSM achieving the best results.

翻译：解释卷积神经网络（CNN）的决策对于理解其行为至关重要，然而可解释性仍然是一个重大挑战，尤其对于自监督模型而言。现有大多数生成显著性图的方法依赖于真实标签，限制了它们在监督任务中的应用。EigenCAM是唯一值得注意的独立于标签的替代方法，它利用奇异值分解生成适用于各种CNN模型的显著性图，但未能充分利用特征图的张量结构。本研究引入了Tucker显著性图（TSM）方法，该方法应用Tucker张量分解以更好地捕捉特征图的固有结构，从而产生更精确的奇异向量和奇异值。这些结果被用于生成高保真度的显著性图，有效突出输入图像中的感兴趣目标。我们进一步将EigenCAM和TSM扩展为多向量变体——多向量EigenCAM（Multivec-EigenCAM）和多向量Tucker显著性图（MTSM），这些变体利用所有奇异向量和奇异值，进一步提升了显著性图的质量。在监督分类模型上的定量评估表明，TSM、Multivec-EigenCAM和MTSM实现了与依赖标签方法相竞争的性能。此外，对于监督和自监督模型，TSM相较于EigenCAM将可解释性提升了约50%。Multivec-EigenCAM和MTSM进一步推进了自监督模型上最先进的可解释性性能，其中MTSM取得了最佳结果。