2 papers
cs.CV2024
Training-free Editioning of Text-to-Image Models
Jinqi Wang, Yunfei Fu, Zhangcan Ding +3
Inspired by the software industry's practice of offering different editions or versions of a product tailored to specific user groups or use cases, we propose a novel task, namely,…
cs.AI2024
Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
Chaoquan Jiang, Jinqiang Wang, Rui Hu +1
Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gainin…