Detect unknown and known objects using CLIP, SAM, and GDINO with cooperative-foundational-models
Detect unknown and known objects using CLIP, SAM, and GDINO with cooperative-foundational-models
Enhancing Novel Object Detection via Cooperative Foundational Models
arXiv paper abstract https://arxiv.org/abs/2311.12068
arXiv PDF paper https://arxiv.org/pdf/2311.12068.pdf
… address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference.
Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD.
… present a novel approach to transform existing closed-set detectors into open-set detectors.
This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through … cooperative mechanism.
Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, … establish new benchmarks in object detection performance.
… method … surpass the current state-of-the-art by a margin of 7.2 AP50 for novel classes …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
