Year: 2018
Type: conference-paper
Abstract: A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable 'explanations' of their decision process, especially for interactive tasks like Visual Question Answering (VQA).In this work, we analyze if existing explanations indeed make a VQA model -its responses as well as failures -more predictable to a human.Surprisingly, we find that they do not.On the other hand, we find that humanin-the-loop approaches that treat the model as a black-box do.
DOI: 10.18653/v1/d18-1128
Authors: Arjun Chandrasekaran, Viraj Prabhu, Deshraj Yadav, Prithvijit Chattopadhyay, Devi Parikh
Institutions: Georgia Institute of Technology, Meta (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G8876996369
OpenAlex ID: W2899448251
