AI models
Adversarial Joint Adaptation Network (ResNet)
Parameters
60M
Published
Aug 17, 2017
Adversarial Joint Adaptation Network (ResNet) is an AI model developed by Tsinghua University and University of California (UC) Berkeley (China and United States), first published in August 2017. It works in the vision domain, on tasks such as image classification.
Epoch AI has no training-compute estimate for this model. The model has 60,000,000 parameters. It was trained on roughly 4.7K datapoints.
The reference paper has 2,743 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Tsinghua University, University of California (UC) Berkeley
- Country of organization
- China, United States
- Domain
- Vision
- Task
- Image classification
- Parameters
- 60,000,000
- Dataset size
- 4.7K
- Numerical format
- FP32
- Citations
- 2,743
- Epoch confidence
- Speculative
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