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

One major impediment in rapidly deploying object detection models forindustrial applications is the lack of large annotated datasets. We currentlyhave presented the Sacked Carton Dataset(SCD) that contains carton images fromthree scenarios, such as comprehensive pharmaceutical logistics company(CPLC),e-commerce logistics company(ECLC), fruit market(FM). However, due to domainshift, the model trained with one of the three scenarios in SCD has poorgeneralization ability when applied to the rest scenarios. To solve thisproblem, a novel image synthesis method is proposed to replace the foregroundtexture of the source datasets with the texture of the target datasets. Ourmethod can keep the context relationship of foreground objects and backgroundsunchanged and greatly augment the target datasets. We firstly propose a surfacesegmentation algorithm to achieve texture decoupling of each instance.Secondly, a contour reconstruction algorithm is proposed to keep the occlusionand truncation relationship of the instance unchanged. Finally, the Gaussianfusion algorithm is used to replace the foreground texture from the sourcedatasets with the texture from the target datasets. The novel image synthesismethod can largely boost AP by at least 4.3%~6.5% on RetinaNet and 3.4%~6.8% onFaster R-CNN for the target domain. Code is available athttps://github.com/hustgetlijun/RCAN.

Carton dataset synthesis method for domain shift based on foreground texture decoupling and replacement