Fragment embedding

Parameters

144.5M

Published

Jun 21, 2014

Fragment embedding is an AI model developed by Stanford University (United States), first published in June 2014. It works in the vision domain, on tasks such as entity embedding and semantic segmentation.

Epoch AI has no training-compute estimate for this model. The model has 144,496,000 parameters. It was trained on roughly 15M datapoints.

Epoch AI rates the confidence of this record as likely.

Full record

Organization: Stanford University
Country of organization: United States
Domain: Vision
Task: Entity embedding, Semantic segmentation
Parameters: 144,496,000
Dataset size: 15M
Epoch confidence: Likely