Version 1
: Received: 26 December 2023 / Approved: 27 December 2023 / Online: 27 December 2023 (10:45:09 CET)
How to cite:
Hambarde, K. Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes. Preprints2023, 2023122087. https://doi.org/10.20944/preprints202312.2087.v1
Hambarde, K. Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes. Preprints 2023, 2023122087. https://doi.org/10.20944/preprints202312.2087.v1
Hambarde, K. Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes. Preprints2023, 2023122087. https://doi.org/10.20944/preprints202312.2087.v1
APA Style
Hambarde, K. (2023). Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes. Preprints. https://doi.org/10.20944/preprints202312.2087.v1
Chicago/Turabian Style
Hambarde, K. 2023 "Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes" Preprints. https://doi.org/10.20944/preprints202312.2087.v1
Abstract
Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.
Keywords
causal inference; deep learning; computer vision; image classification; statistical correlation; causal learning; domain generalization; neural networks; interpretability in AI
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
