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 work, we address the challenging and emergent problem of novel objectdetection (NOD), focusing on the accurate detection of both known and novelobject categories during inference. Traditional object detection algorithms areinherently closed-set, limiting their capability to handle NOD. We present anovel approach to transform existing closed-set detectors into open-setdetectors. This transformation is achieved by leveraging the complementarystrengths of pre-trained foundational models, specifically CLIP and SAM,through our cooperative mechanism. Furthermore, by integrating this mechanismwith state-of-the-art open-set detectors such as GDINO, we establish newbenchmarks in object detection performance. Our method achieves 17.42 mAP innovel object detection and 42.08 mAP for known objects on the challenging LVISdataset. Adapting our approach to the COCO OVD split, we surpass the currentstate-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Ourcode is available athttps://github.com/rohit901/cooperative-foundational-models .

Enhancing Novel Object Detection via Cooperative Foundational Models