Convolutional layers are a fundamental component of most image-related models. These layers often implement by default a static padding policy (\eg zero padding), to control the scale of the internal representations, and to allow kernel activations centered on the border regions. In this work we identify Padding Aware Neurons (PANs), a type of filter that is found in most (if not all) convolutional models trained with static padding. PANs focus on the characterization and recognition of input border location, introducing a spatial inductive bias into the model (e.g., how close to the input's border a pattern typically is). We propose a method to identify PANs through their activations, and explore their presence in several popular pre-trained models, finding PANs on all models explored, from dozens to hundreds. We discuss and illustrate different types of PANs, their kernels and behaviour. To understand their relevance, we test their impact on model performance, and find padding and PANs to induce strong and characteristic biases in the data. Finally, we discuss whether or not PANs are desirable, as well as the potential side effects of their presence in the context of model performance, generalisation, efficiency and safety.

翻译：卷积层是大多数图像相关模型的基础组成部分。这些层通常默认采用静态填充策略（如零填充），以控制内部表示的尺度，并允许核激活集中在边界区域。本研究中，我们识别出感知填充神经元（PANs），这是一种存在于（几乎所有）使用静态填充训练的卷积模型中的滤波器类型。PANs专注于输入边界位置的特征化与识别，向模型引入空间归纳偏差（例如，模式与输入边界接近程度的典型特征）。我们提出了一种通过激活值识别PANs的方法，并探索了其在多个预训练模型中的存在情况，发现所有被研究的模型（从数十个到数百个不等）均包含PANs。我们讨论并展示了不同类型的PANs、其核及行为特征。为理解其相关性，我们测试了它们对模型性能的影响，发现填充与PANs会在数据中引发强烈且特有的偏差。最后，我们探讨了PANs是否具有可取性，以及它们在模型性能、泛化能力、效率与安全性方面可能存在的副作用。