Automatically Searching for U-Net Image Translator Architecture
This work addresses the inefficiency and redundancy in image translation architectures for researchers and practitioners in computer vision, though it is incremental as it builds on existing U-Net frameworks.
The paper tackles the suboptimal adaptation of U-Net for image translation tasks by proposing an automatic architecture search method using evolutionary algorithms, resulting in a more efficient network that reduces computational costs and improves performance, with experiments showing generalization to other datasets.
Image translators have been successfully applied to many important low level image processing tasks. However, classical network architecture of image translator like U-Net, is borrowed from other vision tasks like biomedical image segmentation. This straightforward adaptation may not be optimal and could cause redundancy in the network structure. In this paper, we propose an automatic architecture searching method for image translator. By utilizing evolutionary algorithm, we investigate a more efficient network architecture which costs less computation resources and achieves better performance than the original one. Extensive qualitative and quantitative experiments are conducted to demonstrate the effectiveness of the proposed method. Moreover, we transplant the searched network architecture to other datasets which are not involved in the architecture searching procedure. Efficiency of the searched architecture on these datasets further demonstrates the generalization of the method.