Explainable and Interpretable Models in Computer Vision and Machine Learning

By Hugo Jair Escalante, Sergio Escalera, Isabelle M Guyon, Xavier Baró, Yağmur Güçlütürk, Umut Güçlü, Marcel A. J. van Gerven. 2017

117 citations recorded by the source corpus.

This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning. Research progress in computer vision and pattern recognition has led to a variety of modeling techniques with almost human-like performance. Although these models have obtained astounding results, they are limited in their explainability and interpretability: what is the rationale behind the decision made? what in the model structure explains its functioning? Hence, while good performance is a critical required characteristic for learning machines, explainability and interpretability capabilities are needed to take learning machines to the next step to include them in decision support systems involving human supervision.

Subfields: Artificial Intelligence

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

Citations in the corpus

Conditional variance penalties and domain shift robustness (2017, methodology): “Goudet et al. (2017) use generative neural networks for cause-eﬀect inference, to identify v -structures and to orient the edges of a given graph skeleton.”
Causal Discovery with Reinforcement Learning (2019, background): “ et al., 2014; 2017), and the post-nonlinear causal model (Zhang and Hyvärinen, 2009). Besides Yu et al. (2019); Lachapelle et al. (2019), other recent NN based approaches to causal discovery include Goudet et al. (2018) that proposes causal generative NNs to functional causal 2 Published as a confe”
Interpretability of machine learning‐based prediction models in healthcare (2020, background): “In CV, the focus is on identification of the image sections that are responsible for successful recognition of critical, health condition-specific regions in the image that might be relevant for medical experts (Escalante et al., 2018; Hosny, Parmar, Quackenbush, Schwartz, & Aerts, 2018; Mazurowski,”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, unknown): “[165], [22], [71], [186], [45], [159], [140]) ultimately contributing to further our sci-”
Explainable Artificial Intelligence: Objectives, Stakeholders, and Future Research Opportunities (2020, unknown): “Generalizability refers to the range of models which the XAI technique can explain or be applied to, whereby a high generalizability increases the usefulness of the explanation technique (Ras et al., 2018).”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond (2020, methodology): “Finally as a versatile tool in the sciences, XAI has been allowing to gain novel insights (e.g. [127], [20], [55], [145], [36], [123], [112]) ultimately contributing to further our sci-entiﬁc knowledge.”
Causal Generative Domain Adaptation Networks (2018, methodology): “In the causal discovery (i.e., estimating the underlying causal structure from observational data) ﬁeld [20, 12], some recent methods tried to learn causal graphs by representing functional causal models using neural networks [21].”
Interpretability Framework for LLMs in Undergraduate Calculus (2025, unknown): “Finally, broader surveys in explainable ML [10, 11] identify key metrics of explanatory quality, such as cognitive load, user trust, and task relevance.”