Abstract AutoML (Automated Machine Learning) is an emerging field that aims to automate
the process of building machine learning models. AutoML emerged to increase productivity …

With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving
research area. However, despite promising results, the field still faces challenges that …

Deep learning (DL) techniques have obtained remarkable achievements on various tasks,
such as image recognition, object detection, and language modeling. However, building a …

Deep neural networks have exhibited promising performance in image super-resolution
(SR) by learning a nonlinear map** function from low-resolution (LR) images to high …

Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref)
images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting …

One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of
candidate architectures. Existing methods either directly use the validation performance or …

Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Despite the cross-modal text-to-imagesynthesis task has achieved great success, most of
the latest works in this field are based on the network architectures proposed by …

Multi-scale and multi-patch deep models have been shown effective in removing blurs of
dynamic scenes. However, these methods still have one major obstacle: manually designing …

At present, most mainstream algorithms for single image super-resolution (SISR) assume
the image degradation process as an ideal degradation process (eg bicubic downscaling) …