Ülkü Uzun, Employment Of Cycle-Spinning in Deep Learning
In deep learning, small input shifts or translations can cause dramatic changes in the output. This is because of the fact that commonly used down-sampling techniques such as max pooling, strided convolution, and average pooling ignore the sampling theorem. We have demonstrated that the cycle-spinning (CS) signal processing technique can be used before down-sampling in deep learning to increase accuracy without introducing any extra learnable parameters. The proposed method can be applied to different algorithms such as GAN, classification, and object detection.
Date: 29.11.2022 / 13:00 Place: METU Informatics Institute