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

In this paper we propose a novel method for zero-shot, cross-domain imageretrieval in which we make two key contributions. The first is a test-timere-ranking procedure that enables query-gallery pairs, without meaningfulshared visual features, to be matched by incorporating gallery-gallery ranksinto an iterative re-ranking process. The second is the use of cross-attentionat training time and knowledge distillation to encourage cross-attention-likefeatures to be extracted at test time from a single image. When combined withthe Vision Transformer architecture and zero-shot retrieval losses, ourapproach yields state-of-the-art results on the Sketchy and TU-Berlinsketch-based image retrieval benchmarks. However, unlike many previous methods,none of the components in our approach are engineered specifically towards thesketch-based image retrieval task - it can be generally applied to anycross-domain, zero-shot retrieval task. We therefore also show results onzero-shot cartoon-to-photo retrieval using the Office-Home dataset.

If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval