AI models
Fisher Vector image classifier
Training compute
9.1×10¹³ FLOP
Published
Jun 12, 2013
Fisher Vector image classifier is an AI model developed by Universidad Nacional de Cordoba, Inteligent Systems Lab Amsterdam, University of Amsterdam, LEAR Team, INRIA and Xerox Research Centre Europe (XRCE) (Argentina, Netherlands and France), first published in June 2013. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 9.1×10¹³ FLOP of compute (estimation method: hardware). It was trained on roughly 4.5M datapoints.
The reference paper has 1,707 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Universidad Nacional de Cordoba, Inteligent Systems Lab Amsterdam, University of Amsterdam, LEAR Team, INRIA, Xerox Research Centre Europe (XRCE)
- Country of organization
- Argentina, Netherlands, France
- Domain
- Vision
- Task
- Image classification
- Training compute
- 9.1×10¹³ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 4.5M
- Training time
- 2 h
- Numerical format
- FP32
- Citations
- 1,707
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models