Image Aesthetics Assessment via Learnable Queries
This work addresses the problem of efficient and accurate aesthetics assessment for images, offering a domain-specific incremental improvement.
The paper tackles image aesthetics assessment by proposing IAA-LQ, which uses learnable queries to extract aesthetic features from frozen image encoders, resulting in a 2.2% and 2.1% improvement in SRCC and PLCC over the best state-of-the-art method.
Image aesthetics assessment (IAA) aims to estimate the aesthetics of images. Depending on the content of an image, diverse criteria need to be selected to assess its aesthetics. Existing works utilize pre-trained vision backbones based on content knowledge to learn image aesthetics. However, training those backbones is time-consuming and suffers from attention dispersion. Inspired by learnable queries in vision-language alignment, we propose the Image Aesthetics Assessment via Learnable Queries (IAA-LQ) approach. It adapts learnable queries to extract aesthetic features from pre-trained image features obtained from a frozen image encoder. Extensive experiments on real-world data demonstrate the advantages of IAA-LQ, beating the best state-of-the-art method by 2.2% and 2.1% in terms of SRCC and PLCC, respectively.