paper-with-me

홈 › Papers

VQA-LOL: Visual Question Answering under the Lens of Logic

2020-02-19 · ECCV 2020 8 · Tejas Gokhale, Pratyay Banerjee, Chitta Baral, Yezhou Yang

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 \textit{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 Fr\'echet-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.

📄 PDF Abstract BibTeX arXiv:2002.08325

Code (0)

등록된 구현이 없습니다.

Tasks

NegationQuestion AnsweringSentenceVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering

2026-06-19 · Fengchen Gu, Xiaotian Ren, Zhengyong Jiang, Zhilu Zhang 외 arxiv

Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can…

Question Answering

MaXM: Towards Multilingual Visual Question Answering

2022-09-12 · Soravit Changpinyo, Linting Xue, Michal Yarom, Ashish V. Thapliyal 외

Visual Question Answering (VQA) has been primarily studied through the lens of the English language. Yet, tackling VQA in other languages in the same manner would require a considerable amount of resources. In this paper…

Question AnsweringTranslationVisual Question AnsweringVisual Question Answering (VQA)

FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowcharts

2024-06-27 · Shubhankar Singh, Purvi Chaurasia, Yerram Varun, Pranshu Pandya 외

Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities …

Decision MakingLogical ReasoningQuestion AnsweringSpatial Reasoning+2

Analyzing the Sensitivity of Vision Language Models in Visual Question Answering

2025-07-28 · Monika Shah, Sudarshan Balaji, Somdeb Sarkhel, Sanorita Dey 외 arxiv

We can think of Visual Question Answering as a (multimodal) conversation between a human and an AI system. Here, we explore the sensitivity of Vision Language Models (VLMs) through the lens of cooperative principles of c…

Visual Question Answering

Visual Question Answering based on Formal Logic

2021-11-08 · Muralikrishnna G. Sethuraman, Ali Payani, Faramarz Fekri, J. Clayton Kerce

Visual question answering (VQA) has been gaining a lot of traction in the machine learning community in the recent years due to the challenges posed in understanding information coming from multiple modalities (i.e., ima…

Formal LogicQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)