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：深度神经网络在绝大多数计算机视觉任务中表现出卓越性能。部分关键应用（如自动驾驶或医学影像）还需探究其行为模式与决策依据。由此衍生出的深度神经网络归因研究，旨在分析网络预测结果与输入之间的关联性。现有归因方法已能标注出深度神经网络中最具影响力的权重或神经元，从而更高效地筛选可剪枝的权重要素。然而这类方法存在局限性：通常仅在单层内部比较权重的相对重要性，却可能忽略某些关键性突出的层级。本研究提出对深度神经网络的层级重要性进行分析，即评估层级扰动对模型精度的敏感度。为此我们构建了新型数据集以支撑本方法及后续研究，通过对比多种评估准则，总结出评估深度神经网络层级重要性的有效策略，进而实现层级资源优化分配以提升网络效率（应用于剪枝与量化），同时增强对硬件故障（如比特翻转）的鲁棒性。