VQA-LOL: Visual Question Answering Under the Lens of Logic
Files
Author/Creator
Author/Creator ORCID
Date
Department
Program
Citation of Original Publication
Gokhale, Tejas, Pratyay Banerjee, Chitta Baral, and Yezhou Yang. “VQA-LOL: Visual Question Answering Under the Lens of Logic.” Edited by Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm. Computer Vision – ECCV 2020, 2020, 379–96. https://doi.org/10.1007/978-3-030-58589-1_23.
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Abstract
Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. When put under this Lens of Logic, state-of-the-art VQA models have difficulty in correctly answering these logically composed questions. We construct an augmentation of the VQA dataset as a benchmark, with questions containing logical compositions and linguistic transformations (negation, disjunction, conjunction, and antonyms). We propose our Lens of Logic (LOL) model which uses question-attention and logic-attention to understand logical connectives in the question, and a novel Fréchet-Compatibility Loss, which ensures that the answers of the component questions and the composed question are consistent with the inferred logical operation. Our model shows substantial improvement in learning logical compositions while retaining performance on VQA. We suggest this work as a move towards robustness by embedding logical connectives in visual understanding.