Evaluating the Impact of Color Information in Deep Neural Networks

Buhrmester, Vanessa; Münch, David; Bulatov, Dimitri; Arens, Michael

doi:10.1007/978-3-030-31332-6_27

Cited by 9 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Activation atlases are a novel way to peer into convolutional vision networks and represents a global, hierarchical, and human-interpretable overview of concepts within the hidden layers. Just in the last few months, the importance of interpretability has been growing, which is why there appeared several single studies, investigating the contribution of some aspects of a neural network such as the impact of color [99], texture [24], etc., without explaining a whole model extensively, however, which all contribute to a deeper understanding.…”

Section: Selected Dnn Explainers Presentedmentioning

confidence: 99%

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Buhrmester

Münch

Arens

2021

MAKE

Self Cite

187

View full text Add to dashboard Cite

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

show abstract

Section: Selected Dnn Explainers Presentedmentioning

confidence: 99%

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Buhrmester

Münch

Arens

2021

MAKE

Self Cite

187

View full text Add to dashboard Cite

show abstract

“…The units belonging to the first layers are more sensitive to color, and the later units are more sensitive to the class. Experiments conducted by Buhrmester et al [43] ex-ploring the effect of colour on image classification yielded some interesting results and certain animal and landscape classes depend on the colour information present in the images. They also showed that the color information in some cases are not only increasing the performance of the CNN, and that it is color space dependent.…”

Section: Related Workmentioning

confidence: 99%

Effect of hue shift towards robustness of convolutional neural networks

De¹,

Marius²

2022

View full text Add to dashboard Cite

Computer vision systems become deployed in diverse real time systems hence robustness is a major area of concern. As a vast majority of the AI enabled systems are based on convolutional neural networks based models which use 3-channel RGB images as input. It has been shown that the performance of AI systems, such as those used in classification, is impacted by distortions in the images. To date most work has been carried out on distortions such as noise, blur, compression. However, color related changes to images could also impact the performance. Therefore, the goal of this paper is to study the robustness of these models under different hue shifts.

show abstract

“…Activation atlases is a novel way to peer into convolutional vision networks and represents a global, hierarchical, and human-interpretable overview of concepts within the hidden layers. Just in the last months the importance of interpretability was growing, that is why there appeared several single studies, investigating the contribution of some aspects of a neural network like the impact of color [90], texture [16] etc. without explaining a whole model extensive, however, which all contribute to a deeper understanding.…”

Section: Selected Dnn-explainers Presentedmentioning

confidence: 99%

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Buhrmester¹,

Münch²,

Arens³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

show abstract

Evaluating the Impact of Color Information in Deep Neural Networks

Cited by 9 publications

References 16 publications

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Effect of hue shift towards robustness of convolutional neural networks

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Contact Info

Product

Resources

About