Modern, state-of-the-art Convolutional Neural Networks (CNNs) in computer vision have millions of parameters. Thus, explaining the complex decisions of such networks to humans is challenging. A technical approach to reduce CNN complexity is network pruning, where less important parameters are deleted. The work presented in this paper investigates whether this technical complexity reduction also helps with perceived explainability. To do so, we conducted a pre-study and two human-grounded experiments, assessing the effects of different pruning ratios on CNN explainability. Overall, we evaluated four different compression rates (i.e., CPR 2, 4, 8, and 32) with 37 500 tasks on Mechanical Turk. Results indicate that lower compression rates have a positive influence on explainability, while higher compression rates show negative effects. Furthermore, we were able to identify sweet spots that increase both the perceived explainability and the model's performance.

翻译：现代计算机视觉领域中，最先进的卷积神经网络（CNNs）具有数百万个参数。因此，向人类解释这些网络复杂的决策过程颇具挑战性。降低CNN复杂性的技术手段是网络剪枝，即删除重要性较低的参数。本文探讨了这种技术复杂性的降低是否有助于提升感知上的可解释性。为此，我们开展了一项预研究和两项人类基础实验，评估不同剪枝比例对CNN可解释性的影响。总体而言，我们通过Mechanical Turk平台评估了四种不同的压缩率（即CPR 2、4、8和32），共计37 500项任务。结果表明，较低的压缩率对可解释性具有积极影响，而较高的压缩率则表现出负面效应。此外，我们识别出既能提升感知可解释性又能优化模型性能的最佳平衡点。