Visual Superordinate Abstraction for Robust Concept Learning
文献类型：期刊论文
| 作者 | Qi Zheng3; Chao-Yue Wang1; Dadong Wang2; a-Cheng Tao1,3 |
| 刊名 | Machine Intelligence Research
 |
| 出版日期 | 2023 |
| 卷号 | 20期号:1页码:79-91 |
| 关键词 | Concept learning visual question answering weakly-supervised learning multi-modal learning curriculum learning |
| ISSN号 | 2731-538X |
| DOI | 10.1007/s11633-022-1360-1 |
| 英文摘要 | Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to attribute perturbations and out-of-distribution compositions during inference. We ascribe the bottleneck to a failure to explore the intrinsic semantic hierarchy of visual concepts, e.g., {red, blue,···} “color” subspace yet cube “shape”. In this paper, we propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces (i.e., visual superordinates). With only natural visual question answering data, our model first acquires the semantic hierarchy from a linguistic view and then explores mutually exclusive visual superordinates under the guidance of linguistic hierarchy. In addition, a quasi-center visual concept clustering and superordinate shortcut learning schemes are proposed to enhance the discrimination and independence of concepts within each visual superordinate. Experiments demonstrate the superiority of the proposed framework under diverse settings, which increases the overall answering accuracy relatively by 7.5% for reasoning with perturbations and 15.6% for compositional generalization tests. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55967]  |
| 专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
| 作者单位 | 1.JD Explore Academy, Beijing 100176, China 2.DATA61, Commonwealth Scientific and Industrial Research Organisation, Sydney 2122, Australia 3.University of Sydney, Sydney 2008, Australia |
| 推荐引用方式 GB/T 7714 | Qi Zheng,Chao-Yue Wang,Dadong Wang,et al. Visual Superordinate Abstraction for Robust Concept Learning[J]. Machine Intelligence Research,2023,20(1):79-91. |
| APA | Qi Zheng,Chao-Yue Wang,Dadong Wang,&a-Cheng Tao.(2023).Visual Superordinate Abstraction for Robust Concept Learning.Machine Intelligence Research,20(1),79-91. |
| MLA | Qi Zheng,et al."Visual Superordinate Abstraction for Robust Concept Learning".Machine Intelligence Research 20.1(2023):79-91. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。