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/

Zendy Plus

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

Zendy Tools

Zendy Open

Classifying pill categories from real-world images is crucial for varioussmart healthcare applications. Although existing approaches in imageclassification might achieve a good performance on fixed pill categories, theyfail to handle novel instances of pill categories that are frequently presentedto the learning algorithm. To this end, a trivial solution is to train themodel with novel classes. However, this may result in a phenomenon known ascatastrophic forgetting, in which the system forgets what it learned inprevious classes. In this paper, we address this challenge by introducing theclass incremental learning (CIL) ability to traditional pill imageclassification systems. Specifically, we propose a novel incrementalmulti-stream intermediate fusion framework enabling incorporation of anadditional guidance information stream that best matches the domain of theproblem into various state-of-the-art CIL methods. From this framework, weconsider color-specific information of pill images as a guidance stream anddevise an approach, namely "Color Guidance with Multi-stream intermediatefusion"(CG-IMIF) for solving CIL pill image classification task. We conductcomprehensive experiments on real-world incremental pill image classificationdataset, namely VAIPE-PCIL, and find that the CG-IMIF consistently outperformsseveral state-of-the-art methods by a large margin in different task settings.Our code, data, and trained model are available athttps://github.com/vinuni-vishc/CG-IMIF.

Multi-stream Fusion for Class Incremental Learning in Pill Image Classification