论文标题
训练有素的卷积过滤器中模型到模型分布变化的实证研究
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
论文作者
论文摘要
我们从正在进行的对各种计算机视觉任务的图像数据中的分布变化进行调查中介绍了第一个经验结果。我们建议没有分析原始培训和测试数据，而是建议研究训练有素的模型的学习权重的变化。在这项工作中，我们专注于主要使用的3x3卷积滤波器内核的分布的性能。我们使用广泛的数据集，架构和视觉任务收集并公开提供了来自数百个训练有素的CNN的超过十亿过滤的数据集。我们的分析表明，沿不同轴的元参数轴（例如数据类型，任务，体系结构或层深度）之间的训练过滤器之间的有趣分布变化（或缺乏）。我们认为，观察到的属性是进一步研究进一步研究输入数据中转移对CNN模型的概括和新方法的概括能力的影响的宝贵来源。可用的数据，网址为：https：//github.com/paulgavrikov/cnn-filter-db/。
We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original training and test data, we propose to study shifts in the learned weights of trained models. In this work, we focus on the properties of the distributions of dominantly used 3x3 convolution filter kernels. We collected and publicly provide a data set with over half a billion filters from hundreds of trained CNNs, using a wide range of data sets, architectures, and vision tasks. Our analysis shows interesting distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like data type, task, architecture, or layer depth. We argue, that the observed properties are a valuable source for further investigation into a better understanding of the impact of shifts in the input data to the generalization abilities of CNN models and novel methods for more robust transfer-learning in this domain. Data available at: https://github.com/paulgavrikov/CNN-Filter-DB/.
