2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 194 citations · 48 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningStatistical ModelingCausal Graphical ModelsDomain ModelingCausal Inference From DataCausal Machine LearningCausal Model SpecificationCausal ReasoningCausal RepresentationCausal StructureDomain Generalization
Domain generalization (DG) is essentially an out-of-distribution problem, aiming to generalize the knowledge learned from multiple source domains to an unseen target domain. The mainstream is to leverage statistical models to model the dependence between data and labels, intending to learn representations independent of domain. Nevertheless, the statistical models are superficial descriptions of reality since they are only required to model dependence instead of the intrinsic causal mechanism. When the dependence changes with the target distribution, the statistic models may fail to generalize. In this regard, we introduce a general structural causal model to formalize the DG problem. Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. However, the theoretical idea is far from practical of DG since the required causal/non-causal factors are unobserved. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification. Based on that, we propose a Causality Inspired Representation Learning (CIRL) algorithm that enforces the representations to satisfy the above properties and then uses them to simulate the causal factors, which yields improved generalization ability. Extensive experimental results on several widely used datasets verify the effectiveness of our approach. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> Code is available at “https://github.com/BIT-DA/CIRL”.
48
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das et al. · 2017 · 21.6K citations
Reading digits in natural images with unsupervised feature learning
Yuval Netzer · 2024 · 4.6K citations · Full text
Categorical Reparameterization with Gumbel-Softmax
Eric Jang, Shixiang Gu, Ben Poole · arXiv (Cornell University) · 2016 · 3.2K citations · Full text
Causality: models, reasoning, and inference
Choice Reviews Online · 2000 · 2.9K citations