Back to Case Studies
Zeitview Improves Recall by 12% and Doubles Data Throughput Using Encord
sub hero

Zeitview Improves Recall by 12% and Doubles Data Throughput Using Encord

12.33% increasein recall
3.67% increasein precision
2x increasein labeling speed

Zeitview, a provider of advanced inspection solutions for the energy and infrastructure sectors, significantly improved performance of their rooftop penetration detection model by focusing on high quality data delivery. 

We spoke with Jonathan Lwowski, Head of AI/ML, and Conor Wallace, Machine Learning Engineer, to understand how leveraging Encord helped improve data quality, tightened their feedback loop, and accelerated the deployment of machine learning models into production. 

Key results

Initial training data for Zeitview's rooftop penetration detection models suffered from quality issues. The first dataset was labeled by 15 external contractors using a third-party tool, resulting in inconsistent annotations and suboptimal model performance.


Zeitview improved data quality using the Encord platform: 

  • Moved from external contractors to a smaller, specialized 5-person internal labeling team
  • Implemented robust QA workflows for systematic quality control
  • Relabeled problematic data while simultaneously expanding the dataset


These changes yielded meaningful results:

  • 3.67% boost in precision 
  • 12.33% boost in recall 
  • 2x increase in dataset size and throughput
  • Reduced team size by ⅓


The recall improvement is particularly significant for Zeitview's inspection use case, representing a meaningful enhancement in detection reliability. 

How did Zeitview achieve these results?

Encord's platform enabled several workflow improvements:

  • Consolidate labeling and QA operations within a single environment
  • Implemented structured QA/QC workflows that integrated MLEs directly into the feedback loop
  • Leveraged image similarity search to quickly curate high-quality datasets

As Jonathan notes, labeling data can be expensive and time-consuming if not done efficiently:

"Balancing the cost of obtaining and labeling data with the quality requirements of the project is crucial. Investing in high-quality data can lead to better model performance and more reliable outcomes...” Jonathan Lwowski, Head of AI/ML

Intelligent data curation

For complex projects with no reference data – like rooftop penetrations – Zeitview now leverages image similarity search and image quality metrics to curate high-quality datasets. This approach allows the team to rapidly identify edge cases and ensure diverse training datasets. 

"Rooftop penetrations was a very difficult project to curate data for. We had no pre-existing data in the company database to use for reference so we relied heavily on the image similarity search and image quality metrics in Encord to curate a diverse and high-quality dataset." — Conor Wallace, ML Engineer at Zeitview

blog_image_3074

Automated QA

Zeitview moved from spreadsheet-based feedback to a three-round QA workflow built within Encord, integrating ML engineers directly into the review process. As label accuracy improves, they are able to gradually reduce human oversight.

“The most valuable feature to us is the automated QA workflow that forces the ML engineers to be more incorporated into the labeling process.” — Conor Wallace, ML Engineer at Zeitview

blog_image_3740

Active learning

Zeitview is preparing to use Encord Active to close the loop between model predictions and data curation. The goal: trigger automated retraining when failed predictions are detected, ensuring continuous model improvement.

Summary

Zeitview integrated Encord’s platform to centralize their data operations and automate key parts of the annotation and feedback workflow, enabling greater efficiency and consistency across teams.

With Encord, Zeitview has established a foundation for trustworthy, production-ready datasets and continuous model improvement - delivering faster iteration cycles, higher label quality, and more accurate inspection models.

Explore our products

Frequently asked questions
  • Yes. In addition to being able to train models & run inference using our platform, you can either import model predictions via our APIs & Python SDK, integrate your model in the Encord annotation interface if it is deployed via API, or upload your own model weights.

  • At Encord, we take our security commitments very seriously. When working with us and using our services, you can ensure your and your customer's data is safe and secure. You always own labels, data & models, and Encord never shares any of your data with any third party. Encord is hosted securely on the Google Cloud Platform (GCP). Encord native integrations with private cloud buckets, ensuring that data never has to leave your own storage facility.

    Any data passing through the Encord platform is encrypted both in-transit using TLS and at rest.

    Encord is HIPAA&GDPR compliant, and maintains SOC2 Type II certification. Learn more about data security at Encord here.

  • Yes. If you believe you’ve discovered a bug in Encord’s security, please get in touch at security@encord.com. Our security team promptly investigates all reported issues. Learn more about data security at Encord here.

  • Yes - we offer managed on-demand premium labeling-as-a-service designed to meet your specific business objectives and offer our expert support to help you meet your goals. Our active learning platform and suite of tools are designed to automate the annotation process and maximise the ROI of each human input. The purpose of our software is to help you label less data.

  • The best way to spend less on labeling is using purpose-built annotation software, automation features, and active learning techniques. Encord's platform provides several automation techniques, including model-assisted labeling & auto-segmentation. High-complexity use cases have seen 60-80% reduction in labeling costs.

  • Encord offers three different support plans: standard, premium, and enterprise support. Note that custom service agreements and uptime SLAs require an enterprise support plan. Learn more about our support plans here.

Take control of your ML pipeline with Encord

Forget fragmented workflows, annotation tools, and Notebooks for building AI applications. Encord's Data Development platform accelerates every step of taking your model into production.

Hero image