Based on these two task sets, an optimization-based meta-learning is proposed to learn the generalized NR-IQA model, which can be directly used to evaluate the quality of images with unseen distortions.
Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance.
Different from existing GSM models using hand-crafted scale priors (e. g., the Jeffrey's prior), we propose to learn the scale prior through a deep convolutional neural network (DCNN).
From this adaptation, we split the data in target domain into confident and uncertain subdomains using the proposed uncertainty-based ranking function, through measuring their prediction confidences.
Typical image aesthetics assessment (IAA) is modeled for the generic aesthetics perceived by an ``average'' user.
The underlying idea is to learn the meta-knowledge shared by human when evaluating the quality of images with various distortions, which can then be adapted to unknown distortions easily.
We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects.