AI models
Refined Part Pooling
Training compute
2.6×10¹⁶ FLOP
Published
Jan 9, 2018
Refined Part Pooling is an AI model developed by Tsinghua University, University of Technology Sydney and University of Texas at San Antonio (China, Australia and United States), first published in January 2018. It works in the vision domain, on tasks such as person retrieval.
Training it took an estimated 2.6×10¹⁶ FLOP of compute (estimation method: hardware). It was trained on roughly 77.6K datapoints. Training ran on 2 NVIDIA TITAN Xp for about 1 hours.
The reference paper has 2,377 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Tsinghua University, University of Technology Sydney, University of Texas at San Antonio
- Country of organization
- China, Australia, United States
- Domain
- Vision
- Task
- Person retrieval
- Training compute
- 2.6×10¹⁶ FLOP
- Compute estimation method
- Hardware
- Dataset size
- 77.6K
- Training hardware
- NVIDIA TITAN Xp
- Chips used
- 2
- Training time
- 1 h
- Training power draw
- 1.0 kW
- Citations
- 2,377
- 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