English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Blind image quality assessment (BIQA) aims to automatically evaluate theperceived quality of a single image, whose performance has been improved bydeep learning-based methods in recent years. However, the paucity of labeleddata somewhat restrains deep learning-based BIQA methods from unleashing theirfull potential. In this paper, we propose to solve the problem by a pretexttask customized for BIQA in a self-supervised learning manner, which enableslearning representations from orders of magnitude more data. To constrain thelearning process, we propose a quality-aware contrastive loss based on a simpleassumption: the quality of patches from a distorted image should be similar,but vary from patches from the same image with different degradations andpatches from different images. Further, we improve the existing degradationprocess and form a degradation space with the size of roughly $2\times10^7$.After pre-trained on ImageNet using our method, models are more sensitive toimage quality and perform significantly better on downstream BIQA tasks.Experimental results show that our method obtains remarkable improvements onpopular BIQA datasets.

Quality-aware Pre-trained Models for Blind Image Quality Assessment