.png){kind=icon}
返回
Causal Reasoning Meets Visual Representation Learning: A Prospective Study
.png){kind=icon}
OA
AI
DOI：10.1007/s11633-022-1362-z.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the challenges of the existing visual models. The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge, which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in visual representation learning. This paper aims to provide a comprehensive overview of this emerging field, attract attention, encourage discussions, bring to the forefront the urgency of developing novel causal reasoning methods, publicly available benchmarks, and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.
Keyword:
Causal reasoning
visual representation learning
reliable artificial intelligence
spatial-temporal data
multi-modal analysis
期刊
IF:
8.7
论文数:
304
被引数:
882
机构
引用论文
分享收藏分享收藏Study on Adhesive Strength between Ge2Sb2Te5Film and Electrodes for Phase Change Memory Application
PREAI
分享收藏Distribution, Source Identification, and Assessment of Potentially Toxic Elements in the Sediment Core from the Estuarine Region of the Golmud River to the Qarhan Salt Lake, Qinghai, China.png)
Minerals
OAAI
MineralsIF0
OAAI分享收藏Sodium channel kinetic changes that produce Brugada syndrome or progressive cardiac conduction system disease产生Brugada综合征或进行性心脏传导系统疾病的钠通道动力学变化
PREAI
分享收藏
查看更多内容