Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks. Here, we describe MACO, a simple approach to address these shortcomings. The main idea is to generate images by optimizing the phase spectrum while keeping the magnitude constant to ensure that generated explanations lie in the space of natural images. Our approach yields significantly better results (both qualitatively and quantitatively) and unlocks efficient and interpretable feature visualizations for large state-of-the-art neural networks. We also show that our approach exhibits an attribution mechanism allowing us to augment feature visualizations with spatial importance. We validate our method on a novel benchmark for comparing feature visualization methods, and release its visualizations for all classes of the ImageNet dataset on https://serre-lab.github.io/Lens/. Overall, our approach unlocks, for the first time, feature visualizations for large, state-of-the-art deep neural networks without resorting to any parametric prior image model.

翻译：特征可视化已获得广泛关注，尤其在Olah等人2017年的开创性工作之后，它已成为可解释性研究的关键工具。然而，该技术的普及一直受到限制，原因在于其依赖技巧生成可解释图像，并且在扩展到更深层神经网络时面临相应挑战。本文提出MACO这一简单方法以解决上述缺陷。其核心思想是通过优化相位谱生成图像，同时保持幅度恒定，以确保生成的解释位于自然图像空间。我们的方法在定性和定量评估中均取得显著更好的结果，并为大型先进神经网络实现了高效可解释的特征可视化。我们还证明该方法具有归因机制，能够通过空间重要性信息增强特征可视化效果。我们在用于比较特征可视化方法的新型基准测试中验证了本方法，并在https://serre-lab.github.io/Lens/上发布了ImageNet数据集所有类别的可视化结果。总体而言，我们的方法首次实现了无需依赖任何参数化先验图像模型的大型先进深度神经网络特征可视化。