all AI news
Mitigating attribute amplification in counterfactual image generation
March 15, 2024, 4:45 a.m. | Tian Xia, M\'elanie Roschewitz, Fabio De Sousa Ribeiro, Charles Jones, Ben Glocker
cs.CV updates on arXiv.org arxiv.org
Abstract: Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries. Most work focuses on generating counterfactual images that look plausible, using auxiliary classifiers to enforce effectiveness of simulated interventions. We investigate pitfalls in this approach, discovering the issue of attribute amplification, where unrelated attributes are spuriously affected during interventions, leading to biases across protected characteristics and disease status. We show that attribute amplification is caused by …
abstract arxiv causal classifiers counterfactual cs.ai cs.cv generative image image generation images imaging issue look medical medical imaging modelling queries type work
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US