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

The goal of this work is to establish a scalable pipeline for expanding anobject detector towards novel/unseen categories, using zero manual annotations.To achieve that, we make the following four contributions: (i) in pursuit ofgeneralisation, we propose a two-stage open-vocabulary object detector, wherethe class-agnostic object proposals are classified with a text encoder frompre-trained visual-language model; (ii) To pair the visual latent space (of RPNbox proposals) with that of the pre-trained text encoder, we propose the ideaof regional prompt learning to align the textual embedding space with regionalvisual object features; (iii) To scale up the learning procedure towardsdetecting a wider spectrum of objects, we exploit the available online resourcevia a novel self-training framework, which allows to train the proposeddetector on a large corpus of noisy uncurated web images. Lastly, (iv) toevaluate our proposed detector, termed as PromptDet, we conduct extensiveexperiments on the challenging LVIS and MS-COCO dataset. PromptDet showssuperior performance over existing approaches with fewer additional trainingimages and zero manual annotations whatsoever. Project page with code:https://fcjian.github.io/promptdet.

PromptDet: Towards Open-vocabulary Detection using Uncurated Images