Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear saliency maps and detailed interpretability. To bridge this gap, we propose DecomCAM, a novel decomposition-and-integration method that distills shared patterns from channel activation maps. Utilizing singular value decomposition, DecomCAM decomposes class-discriminative activation maps into orthogonal sub-saliency maps (OSSMs), which are then integrated together based on their contribution to the target concept. Extensive experiments on six benchmarks reveal that DecomCAM not only excels in locating accuracy but also achieves an optimizing balance between interpretability and computational efficiency. Further analysis unveils that OSSMs correlate with discernible object components, facilitating a granular understanding of the model's reasoning. This positions DecomCAM as a potential tool for fine-grained interpretation of advanced deep learning models. The code is avaible at https://github.com/CapricornGuang/DecomCAM.

翻译：解读复杂的深度网络，特别是预训练的视觉语言模型（VLMs），是一项艰巨的挑战。当前的类激活图（CAM）方法能够突出显示揭示模型决策依据的区域，但缺乏清晰的显著性图和详细的解释性。为了弥补这一差距，我们提出了DecomCAM，一种新颖的分解-集成方法，该方法从通道激活图中蒸馏出共享模式。利用奇异值分解，DecomCAM将类判别激活图分解为正交子显著性图（OSSMs），然后根据它们对目标概念的贡献进行集成。在六个基准测试上的大量实验表明，DecomCAM不仅在定位精度上表现出色，而且在可解释性和计算效率之间实现了优化平衡。进一步的分析揭示，OSSMs与可识别的对象组件相关联，有助于对模型推理进行细粒度理解。这使得DecomCAM成为对先进深度学习模型进行细粒度解释的潜在工具。代码可在 https://github.com/CapricornGuang/DecomCAM 获取。