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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent years have witnessed the great success of blind image qualityassessment (BIQA) in various task-specific scenarios, which present invariabledistortion types and evaluation criteria. However, due to the rigid structureand learning framework, they cannot apply to the cross-task BIQA scenario,where the distortion types and evaluation criteria keep changing in practicalapplications. This paper proposes a scalable incremental learning framework(SILF) that could sequentially conduct BIQA across multiple evaluation taskswith limited memory capacity. More specifically, we develop a dynamic parameterisolation strategy to sequentially update the task-specific parameter subsets,which are non-overlapped with each other. Each parameter subset is temporarilysettled to Remember one evaluation preference toward its corresponding task,and the previously settled parameter subsets can be adaptively reused in thefollowing BIQA to achieve better performance based on the task relevance. Tosuppress the unrestrained expansion of memory capacity in sequential taskslearning, we develop a scalable memory unit by gradually and selectivelypruning unimportant neurons from previously settled parameter subsets, whichenable us to Forget part of previous experiences and free the limited memorycapacity for adapting to the emerging new tasks. Extensive experiments oneleven IQA datasets demonstrate that our proposed method significantlyoutperforms the other state-of-the-art methods in cross-task BIQA. The sourcecode of the proposed method is available athttps://github.com/maruiperfect/SILF.

Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment