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

Fine-grained image classification is a challenging problem, since thedifficulty of finding discriminative features. To handle this circumstance,basically, there are two ways to go. One is use attention based method to focuson informative areas, while the other one aims to find high order betweenfeatures. Further, for attention based method there are two directions,activation based and detection based, which are proved effective by scholars.However ,rare work focus on fusing two types of attention with high orderfeature. In this paper, we propose a novel DAF method which fuse two types ofattention and use them to as PAF(part attention filter) in deep bilineartransformation module to mine the relationship between separate parts of anobject. Briefly, our network constructed by a student net who attempt to outputtwo attention maps and a teacher net uses these two maps as empiricalinformation to refine the result. The experiment result shows that only studentnet could get 87.6% accuracy in CUB dataset while cooperating with teacher netcould achieve 89.1% accuracy.

DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification