EaSe: A Diagnostic Tool for VQA based on Answer Diversity

Shailza Jolly, Sandro Pezzelle, Moin Nabi


Abstract
We propose EASE, a simple diagnostic tool for Visual Question Answering (VQA) which quantifies the difficulty of an image, question sample. EASE is based on the pattern of answers provided by multiple annotators to a given question. In particular, it considers two aspects of the answers: (i) their Entropy; (ii) their Semantic content. First, we prove the validity of our diagnostic to identify samples that are easy/hard for state-of-art VQA models. Second, we show that EASE can be successfully used to select the most-informative samples for training/fine-tuning. Crucially, only information that is readily available in any VQA dataset is used to compute its scores.
Anthology ID:
2021.naacl-main.192
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2407–2414
Language:
URL:
https://aclanthology.org/2021.naacl-main.192
DOI:
10.18653/v1/2021.naacl-main.192
Bibkey:
Cite (ACL):
Shailza Jolly, Sandro Pezzelle, and Moin Nabi. 2021. EaSe: A Diagnostic Tool for VQA based on Answer Diversity. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2407–2414, Online. Association for Computational Linguistics.
Cite (Informal):
EaSe: A Diagnostic Tool for VQA based on Answer Diversity (Jolly et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.192.pdf
Optional supplementary data:
 2021.naacl-main.192.OptionalSupplementaryData.zip
Video:
 https://aclanthology.org/2021.naacl-main.192.mp4
Code
 shailzajolly/ease
Data
Visual Question AnsweringVisual Question Answering v2.0