.png){kind=icon}
返回
Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2020.3045034.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Though beneficial for encouraging the visual question answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA data sets are mostly annotated in a crowdsource way, e.g., collecting questions and external reasons from different users via the Internet. In addition to the challenge of knowledge reasoning, how to deal with the annotator bias also remains unsolved, which often leads to superficial overfitted correlations between questions and answers. To address this issue, we propose a novel data set named knowledge-routed visual question reasoning for VQA model evaluation. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed data set aims to cut off the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning. Specifically, we generate the question-answer pair based on both the visual genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases. The programs can select one or two triplets from the scene graph or knowledge base to push multistep reasoning, avoid answer ambiguity, and balance the answer distribution. In contrast to the existing VQA data sets, we further imply the following two major constraints on the programs to incorporate knowledge reasoning. First, multiple knowledge triplets can be related to the question, but only one knowledge relates to the image object. This can enforce the VQA model to correctly perceive the image instead of guessing the knowledge based on the given question solely. Second, all questions are based on different knowledge, but the candidate answers are the same for both the training and test sets. We make the testing knowledge unused during training to evaluate whether a model can understand question words and handle unseen combinations. Extensive experiments with various baselines and state-of-the-art VQA models are conducted to demonstrate that there still exists a big gap between the model with and without groundtruth supporting triplets when given the embedded knowledge base. This reveals the weakness of the current deep embedding models on the knowledge reasoning problem.
Keyword:
Knowledge based systems
Cognition
Visualization
Data models
Knowledge engineering
Context modeling
Annotations
Knowledge understanding
visual question answering (VQA)
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉
OAAI
OAAI分享收藏分享收藏Distinct pattern of c-fos mRNA expression after systemic and intra-accumbens amphetamine and MK-801.png)
Neuroscience
NeuroscienceIF0
PREAI
分享收藏分享收藏Reduced ACTH, while normal β-endorphin CSF levels in early epileptic encephalopathiesPeptides
PeptidesIF0
PREAI
分享收藏
查看更多内容