clip model
Clip_Dataset__NeurIPS2022_ (10)
We find that the performance of the pre-training data varies substantially across distribution shifts, with no single data source dominating.
Technology:
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Sensing and Signal Processing > Image Processing (0.67)
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (0.48)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Country:
- Asia > China > Hong Kong (0.04)
- North America > United States > Illinois > Champaign County > Urbana (0.04)
Genre:
- Research Report > New Finding (1.00)
- Research Report > Experimental Study > Negative Result (0.34)
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (0.72)
- Information Technology > Artificial Intelligence > Natural Language > Chatbot (0.49)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.32)
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
"Effective robustness" measures the extra out-of-distribution (OOD) robustness
Technology:
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
To remedy this, most robust fine-tuning methods aim to preserve the pre-trained features.
Country:
- North America (0.14)
- Asia > China > Hong Kong (0.04)
- Europe (0.04)
Genre:
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (1.00)
Technology:
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.95)
Technology:
Country:
- Europe > Germany > Saarland > Saarbrücken (0.04)
- Europe > France > Île-de-France > Paris > Paris (0.04)
Technology: