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

Interpretability is a crucial factor in building reliable models for variousmedical applications. Concept Bottleneck Models (CBMs) enable interpretableimage classification by utilizing human-understandable concepts as intermediatetargets. Unlike conventional methods that require extensive human labor toconstruct the concept set, recent works leveraging Large Language Models (LLMs)for generating concepts made automatic concept generation possible. However,those methods do not consider whether a concept is visually relevant or not,which is an important factor in computing meaningful concept scores. Therefore,we propose a visual activation score that measures whether the concept containsvisual cues or not, which can be easily computed with unlabeled image data.Computed visual activation scores are then used to filter out the less visibleconcepts, thus resulting in a final concept set with visually meaningfulconcepts. Our experimental results show that adopting the proposed visualactivation score for concept filtering consistently boosts performance comparedto the baseline. Moreover, qualitative analyses also validate that visuallyrelevant concepts are successfully selected with the visual activation score.

Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification