首页|Causal reasoning in typical computer vision tasks

Causal reasoning in typical computer vision tasks

扫码查看
原文链接
  • 万方数据
  • 维普
Deep learning has revolutionized the field of artificial intelligence.Based on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing rapidly.Despite being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to un-controlled factors.Without the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious correlations.As a result,researchers are now trying to enhance deep leaming-based methods with causal theory.Causal theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious correlations.This paper aims to comprehensively review the existing causal methods in typical vision and vision-language tasks such as semantic segmentation,object detection,and image captioning.The advantages of causality and the approaches for building causal paradigms will be summarized.Future roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

causal reasoningcomputer vision tasksvision-language taskssemantic segmentationobject detection

ZHANG KeXuan、SUN QiYu、ZHAO ChaoQiang、TANG Yang

展开 >

Key Laboratory of Advanced Control and Optimization for Chemical Process,Ministry of Education,East China University of Science and Technology,Shanghai 200237,China

National Key Laboratory of Air based Information Perception and Fusion,Luoyang 471000,China

Luoyang Institute of Electro Optical Equipment of Avic,Luoyang 471000,China

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaProgramme of Introducing Talents of Discipline to Universities(the 111 Project)Fundamental Research Funds for the Central UniversitiesShanghai AI Lab

6223300562293502B17017222202317006

2024

10.1007/s11431-023-2502-9

中国科学:技术科学(英文版)
中国科学院

中国科学:技术科学(英文版)

CSTPCDEI
影响因子：1.056
ISSN：1674-7321
年,卷(期)：2024.67(1)
  • 2