IT Pro is supported by its audience. When you purchase through links on our site, we may earn an affiliate commission. Learn more

Microsoft’s new vision-language model outranks humans at image captioning

The company will integrate the new model into Azure Cognitive Services to support vision-language tasks

Microsoft sign on a building

Microsoft researchers have developed a new object-attribute detection model for image encoding: VinVL (visual features in vision-language)

Vision-language (VL) systems make it possible to search relevant images for a text query (or vice versa). They also help describe an image’s content. 

In most cases, the systems use two modules to achieve the VL understanding: an image encoding module to generate feature maps of an input image and a vision-language fusion module to map the encoded image and text into vectors in the same semantic space.

Microsoft’s new research focuses on improving the image-encoding module. When combined with VL fusion modules such as OSCAR and VIVO,  Microsoft’s newest VL system scored big on the most competitive artificial intelligence (AI) benchmarks, including visual question answering (VQA), Microsoft COCO Image Captioning, and novel object captioning (nocaps). 

The tech giant also highlighted that VinVL significantly surpasses human performance on the nocaps leaderboard for consensus-based image description evaluation (CIDEr). 

Microsoft trained its VinVL object-attribute detection model using a large object detection dataset containing 2.49 million images ascribed to 1,848 object classes and 524 attribute classes to achieve the results mentioned above. Microsoft formed the dataset by merging four public object detection datasets (COCO, Open Images, Objects365, and VG).

Related Resource

Getting started with Azure Red Hat OpenShift

A developer’s guide to improving application building and deployment capabilities

How to improve application building and deployment capabilitiesDownload now

“We first pretrained an object detection model on the merged dataset, and then fine-tuned the model with an additional attribute branch on VG, making it capable of detecting both objects and attributes,” said Microsoft.

“Our object-attribute detection model can detect 1,594 object classes and 524 visual attributes. As a result, the model can detect and encode nearly all the semantically meaningful regions in an input image, according to our experiments.”

Despite the promising results, Microsoft said its model is by no means close to the human-level VL understanding. 

Microsoft also announced VinVL would be available to the public for general use. Additionally, it will integrate VinVL into Azure Cognitive Services to power a wide range of Microsoft services, including Image Captioning in Office and LinkedIn, and Seeing AI.

Featured Resources

The Total Economic Impact™ Of Turbonomic Application Resource Management for IBM Cloud® Paks

Business benefits and cost savings enabled by IBM Turbonomic Application Resource Management

Free Download

The Total Economic Impact™ of IBM Watson Assistant

Cost savings and business benefits enabled by Watson Assistant

Free Download

The field guide to application modernisation

Moving forward with your enterprise application portfolio

Free Download

AI for customer service

Discover the industry-leading AI platform that customers and employees want to use

Free Download

Recommended

Microsoft blocking Tutanota users from Teams registration, claims fix unfeasible
Business operations

Microsoft blocking Tutanota users from Teams registration, claims fix unfeasible

8 Aug 2022
Microsoft wins five-year digital transformation deal with Australia’s largest telco
digital transformation

Microsoft wins five-year digital transformation deal with Australia’s largest telco

26 Jul 2022
Slack Connect vs Microsoft Teams Connect: Better than email?
collaboration

Slack Connect vs Microsoft Teams Connect: Better than email?

20 Jul 2022
Microsoft announces simulator for autonomous aircraft development
Cloud

Microsoft announces simulator for autonomous aircraft development

20 Jul 2022

Most Popular

UK water supplier confirms hack by Cl0p ransomware gang
ransomware

UK water supplier confirms hack by Cl0p ransomware gang

16 Aug 2022
Why convenience is the biggest threat to your security
Sponsored

Why convenience is the biggest threat to your security

8 Aug 2022
How to boot Windows 11 in Safe Mode
Microsoft Windows

How to boot Windows 11 in Safe Mode

29 Jul 2022