Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.
翻译:尽管在调查高效网络结构、优化器和培训战略方面已经付出了很大努力,但图像内插对神经网络性能的影响并没有很好地研究。此外,研究还表明,神经网络往往敏感地注意输入图像的微小变化,导致其性能急剧下降。因此,我们提议使用关键点不可知频率选择性网对网取样(FSMR)处理神经网络的输入数据。这种基于模型的内插方法已经表明,它有能力在PSNR方面超越共同的内插方法。我们利用广泛的实验性评估表明,根据网络结构和分类任务,FSMR在培训过程中的应用有助于学习过程。此外,我们表明,在应用阶段使用FSMR是有益的。ResNet50和Ox Flowl17数据集的分类精确率可以提高到4.31个百分点。