Improving Users' Mental Model with Attention-directed Counterfactual Edits

no code implementations • 13 Oct 2021 • Kamran Alipour, Arijit Ray, Xiao Lin, Michael Cogswell, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas

In the domain of Visual Question Answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain Image-Question (IQ) pairs.

Question Answering Retrieval +1

The Impact of Explanations on AI Competency Prediction in VQA

no code implementations • 2 Jul 2020 • Kamran Alipour, Arijit Ray, Xiao Lin, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas

In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA).

Language Modelling Question Answering +1

Deep Learning Improves Contrast in Low-Fluence Photoacoustic Imaging

no code implementations • 19 Apr 2020 • Ali Hariri, Kamran Alipour, Yash Mantri, Jurgen P. Schulze, Jesse V. Jokerst

We suggest that this tool can improve the value of such sources in photoacoustic imaging.

Denoising SSIM

A Study on Multimodal and Interactive Explanations for Visual Question Answering

no code implementations • 1 Mar 2020 • Kamran Alipour, Jurgen P. Schulze, Yi Yao, Avi Ziskind, Giedrius Burachas

Explainability and interpretability of AI models is an essential factor affecting the safety of AI.

Question Answering Visual Question Answering (VQA)