Explaining Visual Models by Causal Attribution

Martinez, Alvaro Parafita; Vitrià, Jordi

doi:10.1109/iccvw.2019.00512

Cited by 12 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It provides a classification of existing work in four main categories, i.e., causal inference and model-based interpretation, example-based interpretation, fairness, and guarantee of interoperability. The approaches [29][30][31][32] focus on explaining the causal role of different components of the deep neural network in establishing final predictions by calculating average causal effects or establishing a surrogate structural causal model.…”

Section: Causal Interpretabilitymentioning

confidence: 99%

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Choudhary,

Vuković,

Mutlu

et al. 2024

Preprint

View full text Add to dashboard Cite

In a dynamic production processes, mechanical degradation poses a significant challenge, impacting product quality and process efficiency. This paper explores a novel approach for monitoring degradation in the context of viscose fiber production, a highly dynamic manufacturing process. Using causal discovery techniques, our method allows domain experts to incorporate background knowledge into the creation of causal graphs. Further, it enhances the interpretability and increases the ability to identify potential problems via changes in causal relations over time. The case study employs a comprehensive analysis of the viscose fiber production process within a prominent textile industry, emphasizing the advantages of causal discovery for monitoring degradation. The results are compared with state-of-the-art methods, which are not considered to be interpretable, specifically LSTM-based autoencoders, showcasing the alignment and validation of our approach. This paper provides valuable information on degradation monitoring strategies, demonstrating the efficacy of causal discovery in dynamic manufacturing environments. The findings contribute to the evolving landscape of process optimization and quality control.

show abstract

Section: Causal Interpretabilitymentioning

confidence: 99%

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Choudhary,

Vuković,

Mutlu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…It provides a classification of existing work into four main categories, that is, causal inference and model-based interpretation, example-based interpretation, fairness, and guarantee of interoperability. The approaches [49][50][51][52] focus on explaining the causal role of different components of the deep neural network in establishing final predictions by calculating average causal effects or establishing a surrogate structural causal model.…”

Section: Interpreting Complex Systems: Explainable Ai Vs Causal Inter...mentioning

confidence: 99%

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Choudhary,

Vuković,

Mutlu

et al. 2024

Sensors

View full text Add to dashboard Cite

In a dynamic production processes, mechanical degradation poses a significant challenge, impacting product quality and process efficiency. This paper explores a novel approach for monitoring degradation in the context of viscose fiber production, a highly dynamic manufacturing process. Using causal discovery techniques, our method allows domain experts to incorporate background knowledge into the creation of causal graphs. Further, it enhances the interpretability and increases the ability to identify potential problems via changes in causal relations over time. The case study employs a comprehensive analysis of the viscose fiber production process within a prominent textile industry, emphasizing the advantages of causal discovery for monitoring degradation. The results are compared with state-of-the-art methods, which are not considered to be interpretable, specifically LSTM-based autoencoder, UnSupervised Anomaly Detection on Multivariate Time Series (USAD), and Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data (TranAD), showcasing the alignment and validation of our approach. This paper provides valuable information on degradation monitoring strategies, demonstrating the efficacy of causal discovery in dynamic manufacturing environments. The findings contribute to the evolving landscape of process optimization and quality control.

show abstract

“…With the development of deep learning across industries and disciplines, the applications of deep learning models in real-world scenes require a high degree of robustness, interpretability, and transparency. Unfortunately, the black-box properties of deep neural networks are still not fully explainable, and many machine decisions are still poorly understood [219] . In recent years, causal interpretability has received increasing attention.…”

Section: Counterfactual Interventionmentioning

confidence: 99%

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

et al. 2022

View full text Add to dashboard Cite

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the challenges of the existing visual models. The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge, which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in visual representation learning. This paper aims to provide a comprehensive overview of this emerging field, attract attention, encourage discussions, bring to the forefront the urgency of developing novel causal reasoning methods, publicly available benchmarks, and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.

show abstract

Explaining Visual Models by Causal Attribution

Cited by 12 publications

References 10 publications

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

Contact Info

Product

Resources

About