Language-assisted Vision Model Debugger

Vision models with high overall accuracy often exhibit systematic errors on some important subsets of data, posing potential serious safety concerns. Diagnosing such bugs of vision models is gaining increased attention, but traditional diagnostic methods require labor-intensive data collection and attributes annotation.

Data and Resources

Cite this as

Chaoquan Jiang, Jinqiang Wang, Rui Hu, Jitao Sang (2024). Dataset: Language-assisted Vision Model Debugger. https://doi.org/10.57702/jfmpioih

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2312.05588
Author Chaoquan Jiang
More Authors
Jinqiang Wang
Rui Hu
Jitao Sang
Homepage https://arxiv.org/abs/2304.12345