Deconfounded Visual Question Generation with Causal Inference

计算机科学 推论 人工智能 因果推理 自然语言处理 计量经济学 数学
作者
Jiali Chen,Zhen‐Ren Guo,Jiayuan Xie,Yi Cai,Qing Li
标识
DOI:10.1145/3581783.3612536
摘要

Visual Question Generation (VQG) task aims to generate meaningful and logically reasonable questions about the given image targeting an answer. Existing methods mainly focus on the visual concepts present in the image for question generation and have shown remarkable performance in VQG. However, these models frequently learn highly co-occurring object relationships and attributes, which is an inherent bias in question generation. This previously overlooked bias causes models to over-exploit the spurious correlations among visual features, the target answer, and the question. Therefore, they may generate inappropriate questions that contradict the visual content or facts. In this paper, we first introduce a causal perspective on VQG and adopt the causal graph to analyze spurious correlations among variables. Building on the analysis, we propose a Knowledge Enhanced Causal Visual Question Generation (KECVQG) model to mitigate the impact of spurious correlations in question generation. Specifically, an interventional visual feature extractor (IVE) is introduced in KECVQG, which aims to obtain unbiased visual features by disentangling. Then a knowledge-guided representation extractor (KRE) is employed to align unbiased features with external knowledge. Finally, the output features from KRE are sent into a standard transformer decoder to generate questions. Extensive experiments on the VQA v2.0 and OKVQA datasets show that KECVQG significantly outperforms existing models.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
量子星尘发布了新的文献求助10
刚刚
酷波er应助quzhenzxxx采纳,获得10
3秒前
4秒前
cqy关注了科研通微信公众号
4秒前
CipherSage应助Matthewwt采纳,获得10
4秒前
4秒前
4秒前
可乐完成签到,获得积分10
5秒前
李浩发布了新的文献求助10
5秒前
6秒前
大个应助you998308采纳,获得10
7秒前
桐桐应助xzs采纳,获得10
8秒前
後zgw完成签到,获得积分10
8秒前
馒头完成签到,获得积分10
9秒前
DianaRang发布了新的文献求助50
9秒前
12秒前
15秒前
Guohao发布了新的文献求助10
15秒前
受伤白昼完成签到,获得积分10
16秒前
17秒前
18秒前
19秒前
乖猫要努力应助可露丽采纳,获得10
20秒前
cqy发布了新的文献求助10
20秒前
23秒前
24秒前
莫言发布了新的文献求助10
24秒前
25秒前
Frankenstein发布了新的文献求助10
25秒前
miya完成签到,获得积分10
26秒前
xzs发布了新的文献求助10
27秒前
无语的凡梦完成签到,获得积分10
27秒前
27秒前
27秒前
29秒前
30秒前
yanzu完成签到,获得积分0
31秒前
31秒前
32秒前
quzhenzxxx发布了新的文献求助10
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971644
求助须知:如何正确求助?哪些是违规求助? 3516269
关于积分的说明 11181862
捐赠科研通 3251441
什么是DOI,文献DOI怎么找? 1795889
邀请新用户注册赠送积分活动 876131
科研通“疑难数据库(出版商)”最低求助积分说明 805246