Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also require investigation into their behavior and the reasons behind the decisions they make. In this vein, DNN attribution consists in studying the relationship between the predictions of a DNN and its inputs. Attribution methods have been adapted to highlight the most relevant weights or neurons in a DNN, allowing to more efficiently select which weights or neurons can be pruned. However, a limitation of these approaches is that weights are typically compared within each layer separately, while some layers might appear as more critical than others. In this work, we propose to investigate DNN layer importance, i.e. to estimate the sensitivity of the accuracy w.r.t. perturbations applied at the layer level. To do so, we propose a novel dataset to evaluate our method as well as future works. We benchmark a number of criteria and draw conclusions regarding how to assess DNN layer importance and, consequently, how to budgetize layers for increased DNN efficiency (with applications for DNN pruning and quantization), as well as robustness to hardware failure (e.g. bit swaps).

翻译：摘要：深度神经网络（DNN）在大多数计算机视觉任务中展现出卓越性能。某些关键应用（如自动驾驶或医学影像）还需探究其行为模式及决策依据。在此背景下，DNN归因分析旨在研究网络预测结果与输入之间的关联。现有归因方法已被改造用于突出DNN中最具相关性的权重或神经元，从而更高效地选择可剪枝的权重或神经元。然而，这些方法的局限性在于权重通常仅在单层内进行横向比较，而部分层级可能表现出更高的关键性。本研究提出了针对DNN层重要性的分析方法，即评估精度对层级扰动的灵敏度。为此，我们构建了新型数据集以验证本方法及后续研究。通过基准测试多项评估准则，我们总结了DNN层级重要性的判定方法，并据此提出了层级预算分配策略——既能提升DNN效率（应用于剪枝与量化），又能增强对硬件故障（如比特翻转）的鲁棒性。