Explaining Visual Models by Causal Attribution
By Álvaro Parafita, Jordi Vitrià. 2019
39 citations recorded by the source corpus.
Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Divyat Mahajan
- Ruocheng Guo
- Chenhao Tan
- Amit Sharma
- Matthew R. O'Shaughnessy
- Raha Moraffah
- Mansooreh Karami
- Christopher J. Rozell
In Computer Vision and Pattern Recognition
- Matthew R. O'Shaughnessy
- Raha Moraffah
- Divyat Mahajan
- Amit Sharma
- Mansooreh Karami
- Christopher J. Rozell
- Mark A. Davenport
- Adrienne Jeanisha Raglin
Citations in the corpus
- Causal Interpretability for Machine Learning - Problems, Methods and Evaluation (2020, background): “Traditional Interpretability Interpretable Models: [107], [104], [64], [103], [65], [106], [50], [13], [40] Causal Interpretability Model-based: [77], [38], [12], [8], [113], [81], [7], Example-based: [35], [45], [39], [101], [76], [86], [73], [61], [60], [33], [34] Post-hoc: [47], [89], [66], [93],”
- Generative causal explanations of black-box classifiers (2020, methodology): “Generative models have been used to compute interventions that respect the data distribution [51, 36, 19, 52], a key idea in this paper.”
- Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers (2019, methodology): “[15] propose a method on generating CF explanations as interventions on a structural causal model but their approach depends on full knowledge of structural causal model.”