paper-with-me

홈 › Papers

Maintaining Reasoning Consistency in Compositional Visual Question Answering

2022-01-01 · CVPR 2022 1 · Chenchen Jing, Yunde Jia, Yuwei Wu, Xinyu Liu, Qi Wu

A compositional question refers to a question that contains multiple visual concepts (e.g., objects, attributes, and relationships) and requires compositional reasoning to answer. Existing VQA models can answer a compositional question well, but cannot work well in terms of reasoning consistency in answering the compositional question and its sub-questions. For example, a compositional question for an image is: "Are there any elephants to the right of the white bird?" and one of its sub-questions is " Is any bird visible in the scene?". The models may answer "yes" to the compositional question, but "no" to the sub-question. This paper presents a dialog-like reasoning method for maintaining reasoning consistency in answering a compositional question and its sub-questions. Our method integrates the reasoning processes for the sub-questions into the reasoning process for the compositional question like a dialog task, and uses a consistency constraint to penalize inconsistent answer predictions. In order to enable quantitative evaluation of reasoning consistency, we construct a GQA-Sub dataset based on the well-organized GQA dataset. Experimental results on the GQA dataset and the GQA-Sub dataset demonstrate the effectiveness of our method.

📄 PDF Abstract BibTeX

Code (1)

jingchenchen/reasoningconsistency-vqa 공식 구현 pytorch

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Measuring Compositional Consistency for Video Question Answering

2022-04-14 · CVPR 2022 1 · Mona Gandhi, Mustafa Omer Gul, Eva Prakash, Madeleine Grunde-McLaughlin 외

Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositional reasoning cause models to mispredict. …

Question AnsweringVideo Question Answering

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

2019-02-25 · CVPR 2019 6 · Drew A. Hudson, Christopher D. Manning

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine th…

Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering

2024-07-03 · CVPR 2024 1 · Zhaohe Liao, Jiangtong Li, Li Niu, Liqing Zhang

Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional re…

Contrastive LearningLanguage ModellingLarge Language ModelQuestion Answering+2

Detection-based Intermediate Supervision for Visual Question Answering

2023-12-26 · Yuhang Liu, Daowan Peng, Wei Wei, Yuanyuan Fu 외

Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning. NMNs decompose the complex question int…

cross-modal alignmentLogical ReasoningQuestion AnsweringVisual Question Answering

Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering

2024-04-05 · Lili Liang, Guanglu Sun, Jin Qiu, Lizhong Zhang

Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are cruci…

Question AnsweringVideo Question Answering