PeopleofSuperintelligence

Researcher

Nathan Silberman

Nathan Silberman is a computer-vision researcher whose work spans indoor-scene understanding, machine-learning systems and clinical AI. With Rob Fergus, he published indoor-scene research in 2011 and coauthored an ECCV paper on support inference in 2012; in 2015, he coauthored Im2Calories, which predicts meal nutrition from images. At Google Research, he and Sergio Guadarrama published TensorFlow-Slim in 2016, and in 2019 he coauthored a CVPR method for learning from noisy labels. The 2012 indoor-segmentation paper received ECCV’s Koenderink Prize in 2022; in June 2024, he led machine learning and engineering at Artera after vice-president roles at Butterfly Network and PathAI. As of October 2026, he is ArteraAI’s Chief Technology Officer, holds BA and PhD degrees from New York University, and his team develops prognostic and predictive AI products to personalize cancer therapy.

Now at
ArteraAI
Works
31
Citations
10,473
h-index
15
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2011

    Indoor scene segmentation

    In 2011, he and Rob Fergus publish “Indoor scene segmentation using a structured light sensor.”

  2. 2012

    Indoor segmentation and support inference

    With Derek Hoiem, Pushmeet Kohli and Rob Fergus, he coauthors “Indoor Segmentation and Support Inference from RGBD Images” at ECCV in 2012. The paper parses indoor RGB-D scenes into floors, walls, supporting surfaces and object regions, and recovers support relationships.

  3. 2015

    Im2Calories food recognition

    In 2015, he coauthors Im2Calories, a mobile vision system that recognizes food in a meal image and predicts nutritional contents such as calories.

  4. 2016

    Building TensorFlow-Slim

    At Google Research, he and Sergio Guadarrama publish TensorFlow-Slim in 2016. The library gives users high-level tools to define, train and evaluate TensorFlow models.

  5. 2019

    Learning from noisy labels

    In 2019, he coauthors a CVPR paper that learns individual annotator models and the underlying true label distribution from noisy observations.

  6. 2022

    A Koenderink Prize

    In 2022, ECCV awards the Koenderink Prize to “Indoor Segmentation and Support Inference from RGBD Images,” coauthored by Silberman, Derek Hoiem, Pushmeet Kohli and Rob Fergus.

  7. June 2024

    Machine learning at Artera

    In June 2024, he leads machine learning and engineering at Artera as Vice President of Machine Learning and Engineering. Before Artera, he serves as Vice President of Artificial Intelligence at Butterfly Network and Vice President of Machine Learning at PathAI.

  8. As of October 2026

    Chief technology officer

    As of October 2026, he is ArteraAI’s Chief Technology Officer and holds a BA and PhD from New York University. His team develops prognostic and predictive AI products to personalize cancer therapy.

Career

  1. NowArteraAIChief Technology Officer
  2. Until 2024Butterfly Network
  3. Until 2024PathAI
  4. 2016Google Research
  5. 2016–2020Google
  6. ArteraVice President of Machine Learning and Engineering

Education

  1. New York UniversityBA

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Indoor Segmentation and Support Inference from RGBD Images2012 · Lecture notes in computer science · 5,749 citationsWith Derek Hoiem, Pushmeet Kohli and Rob Fergus
  2. Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks2017 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 1,601 citationsWith Dumitru Erhan
  3. Domain Separation Networks2016 · 1,208 citationsWith Dumitru Erhan
  4. Indoor scene segmentation using a structured light sensor2011 · IEEE International Conference on Computer Vision Workshops · 490 citationsWith Rob Fergus
  5. Im2Calories: Towards an Automated Mobile Vision Food Diary2015 · IEEE International Conference on Computer Vision (ICCV) · 485 citationsWith George Papandreou, Kevin P. Murphy and Sergio Guadarrama

From OpenAlex, as of 21 October 2026.

  1. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Google. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Nathan Silberman yet. Send us a free-licensed photo.

  1. Indoor scene segmentation using a structured light sensor | Metascience Observatory explore.metascienceobservatory.org. Checked 21 October 2026.
  2. Indoor segmentation and support inference from RGBD images - Illinois Experts experts.illinois.edu. Checked 21 October 2026.
  3. Im2Calories: towards an automated mobile vision food diary research.google. Checked 21 October 2026.
  4. TF-Slim: A high level library to define complex models in TensorFlow research.google. Checked 21 October 2026.
  5. Learning From Noisy Labels by Regularized Estimation of Annotator Confusion - Microsoft Research microsoft.com. Checked 21 October 2026.
  6. ECVA | European Computer Vision Association ecva.net. Checked 21 October 2026.
  7. Nathan Silberman | ArteraAI artera.ai. Checked 21 October 2026.
  8. Personalized Cancer Treatment Decisions with Nathan Silberman from Artera pixelscientia.com. Checked 21 October 2026.