Back to Blogs

Announcing the launch of SAM 2 in Encord

December 18, 2024
|
2 mins
blog image

In April 2023, we introduced the original SAM model to our platform a mere few days after its initial release. Today, we are excited to announce the integration of Meta’s new Segment Anything Model, SAM 2, into our automated labelling suite, just one day after its official release. This rapid integration underscores our commitment to providing our customers with access to cutting-edge machine learning techniques faster than ever before.

Integrating SAM 2 brings enhanced accuracy and speed to your automated segmentation workflows, enhancing both throughput and user experience. We’re starting today by bringing SAM 2 into image segmentation tasks, where it’s been benchmarked to perform up to 6x faster than SAM. We are also looking forward to introducing the VOS capabilities of SAM 2, enhancing performance on automating video segmentation technologies already in Encord, such as SAM + Cutie.

Supercharge Your Annotations with the
Segment Anything Model
Label with SAM in Encord
medical banner

As an extremely new piece of technology, SAM 2 is being made available to all our customers via Encord Labs. To enable SAM 2, navigate to Encord Labs in your settings and enable the switch for SAM 2, as illustrated in our documentation. When you return to the editor, you’ll know SAM 2 is enabled by the enhanced magic wand icon in the editor, signalling that you are using the latest and most powerful tools for your annotation tasks.

blog_image_3144

How Encord's SAM 2 Integration Increased Annotation Efficiency & Cost Savings for Plainsight

Plainsight faced significant challenges with their in-house data pipelines, which were resource-intensive and inefficient. Their homegrown solutions struggled to meet their high-standards, diverting focus from their core mission.

Encord’s Automated Labeling Suite, including tools like SAM 2 assisted labeling, boosted annotator productivity, reduced manual annotation time and costs by approximately 50%.

Kit (CEO, Plainsight) says, “Before using Encord, it was challenging to see all the data, projects, and annotations in one place. I constantly had to ask questions to understand what was going on. Now, with Encord I feel like we have a much clearer understanding of everything that's happening.”

Plainsight transitioned to Encord’s data development platform, which seamlessly integrated with their existing pipelines. Encord provided robust data management, automated annotation tools, and granular curation features, enabling Plainsight to eliminate their inefficient in-house solutions and focus on core objectives.

The Plainsight team specifically mentioned the automated annotation tooling, notably the SAM 2 model, as a key improvement over their previous set-up.

Read the full Plainsight Case Study to see how you can also slash data management overhead.

Try Out Encord's SAM 2 Integration

We are eager for our customers to try out SAM 2 and experience its benefits firsthand. We believe that this integration will significantly enhance the capabilities of our platform and provide unparalleled accuracy and speed in data annotation. We invite all users to send their feedback to product@encord.com. Your insights are invaluable as we continue to push the boundaries of what’s possible in machine learning annotation and evaluation.

Thank you for being a part of this exciting journey with Encord. We look forward to continuing to deliver world-leading technology at a rapid pace to meet the needs of our innovative customers.

To implement the SAM 2 model, read our comprehensive guide on How To Fine-Tune Segment Anything, which also includes a Colab notebook as a walkthrough.

encord logo

Power your AI models with the right data

Automate your data curation, annotation and label validation workflows.

Get started
Written by
author-avatar-url

Justin Sharps

View more posts
Frequently asked questions
  • SAM 2 (Segment Anything Model 2) is Meta’s latest version of its segmentation model. Compared to the original SAM, SAM 2 delivers up to 6x faster performance and improved accuracy in segmentation tasks, enhancing the speed and precision of automated workflows.
  • Navigate to Encord Labs in your settings. Toggle the switch for SAM 2. Return to the editor, where you’ll see an enhanced magic wand icon, indicating SAM 2 is active.
  • SAM 2 is initially integrated for image segmentation tasks. Future updates will incorporate SAM 2's video object segmentation (VOS) capabilities to enhance automated video annotation workflows.
  • Faster workflows: Up to 6x faster than SAM. Improved accuracy: Higher precision in segmentation results. Better user experience: Seamless integration into Encord’s automated labeling suite.

Explore our products