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

In this paper, we propose Suppression-Enhancing Mask based attention andInteractive Channel transformatiON (SEMICON) to learn binary hash codes fordealing with large-scale fine-grained image retrieval tasks. In SEMICON, wefirst develop a suppression-enhancing mask (SEM) based attention to dynamicallylocalize discriminative image regions. More importantly, different fromexisting attention mechanism simply erasing previous discriminative regions,our SEM is developed to restrain such regions and then discover othercomplementary regions by considering the relation between activated regions ina stage-by-stage fashion. In each stage, the interactive channel transformation(ICON) module is afterwards designed to exploit correlations across channels ofattended activation tensors. Since channels could generally correspond to theparts of fine-grained objects, the part correlation can be also modeledaccordingly, which further improves fine-grained retrieval accuracy. Moreover,to be computational economy, ICON is realized by an efficient two-step process.Finally, the hash learning of our SEMICON consists of both global- andlocal-level branches for better representing fine-grained objects and thengenerating binary hash codes explicitly corresponding to multiple levels.Experiments on five benchmark fine-grained datasets show our superiority overcompeting methods.

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval