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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image retrieval plays an important role in the Internet world. Usually, thecore parts of mainstream visual retrieval systems include an online service ofthe embedding model and a large-scale vector database. For traditional modelupgrades, the old model will not be replaced by the new one until theembeddings of all the images in the database are re-computed by the new model,which takes days or weeks for a large amount of data. Recently,backward-compatible training (BCT) enables the new model to be immediatelydeployed online by making the new embeddings directly comparable to the oldones. For BCT, improving the compatibility of two models with less negativeimpact on retrieval performance is the key challenge. In this paper, weintroduce AdvBCT, an Adversarial Backward-Compatible Training method with anelastic boundary constraint that takes both compatibility and discriminationinto consideration. We first employ adversarial learning to minimize thedistribution disparity between embeddings of the new model and the old model.Meanwhile, we add an elastic boundary constraint during training to improvecompatibility and discrimination efficiently. Extensive experiments on GLDv2,Revisited Oxford (ROxford), and Revisited Paris (RParis) demonstrate that ourmethod outperforms other BCT methods on both compatibility and discrimination.The implementation of AdvBCT will be publicly available athttps://github.com/Ashespt/AdvBCT.

Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval