Publication Type
Journal Article
Version
acceptedVersion
Publication Date
1-2023
Abstract
Deep learning models often fit undesired dataset bias in training. In this paper, we formulate the bias using causal inference, which helps us uncover the ever-elusive causalities among the key factors in training, and thus pursue the desired causal effect without the bias. We start from revisiting the process of building a visual recognition system, and then propose a structural causal model (SCM) for the key variables involved in dataset collection and recognition model: object, common sense, bias, context, and label prediction. Based on the SCM, one can observe that there are “good” and “bad” biases. Intuitively, in the image where a car is driving on a high way in a desert, the “good” bias denoting the common-sense context is the highway, and the “bad” bias accounting for the noisy context factor is the desert. We tackle this problem with a novel causal interventional training (CIT) approach, where we control the observed context in each object class. We offer theoretical justifications for CIT and validate it with extensive classification experiments on CIFAR-10, CIFAR-100 and ImageNet, e.g., surpassing the standard deep neural networks ResNet-34 and ResNet-50, respectively, by 0.95% and 0.70% accuracies on the ImageNet. Our code is open-sourced on the GitHub https://github.com/qinwei-hfut/CIT.
Keywords
Image recognition, causality, causal intervention, deep learning, ImageNet
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
IEEE Transactions on Multimedia
Volume
25
First Page
1033
Last Page
1044
ISSN
1520-9210
Identifier
10.1109/TMM.2021.3136717
Publisher
Institute of Electrical and Electronics Engineers
Citation
QIN, Wei; ZHANG, Hanwang; HONG, Richang; LIM, Ee-Peng; and SUN, Qianru.
Causal interventional training for image recognition. (2023). IEEE Transactions on Multimedia. 25, 1033-1044.
Available at: https://ink.library.smu.edu.sg/sis_research/6743
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/TMM.2021.3136717
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons