Rethinking Persistent Homology For Visual Recognition

Ekaterina Khramtsova, Guido Zuccon, Xi Wang, Mahsa Baktashmotlagh
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:206-215, 2022.

Abstract

Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing research in this area focuses primarily on efficiently integrating topological properties of the data in the learning process in order to enhance the performance. However, there is no existing study to demonstrate all possible scenarios where introducing topological properties can boost or harm the performance. This paper performs a detailed analysis of the effectiveness of topological properties for image classification in various training scenarios, defined by: the number of training samples, the complexity of the training data and the complexity of the backbone network. We identify the scenarios that benefit the most from topological features, e.g., training simple networks on small datasets. Additionally, we discuss the problem of topological consistency of the datasets which is one of the major bottlenecks for using topological features for classification. We further demonstrate how the topological inconsistency can harm the performance for certain scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-khramtsova22a, title = {Rethinking Persistent Homology For Visual Recognition}, author = {Khramtsova, Ekaterina and Zuccon, Guido and Wang, Xi and Baktashmotlagh, Mahsa}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {206--215}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/khramtsova22a/khramtsova22a.pdf}, url = {https://proceedings.mlr.press/v196/khramtsova22a.html}, abstract = {Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing research in this area focuses primarily on efficiently integrating topological properties of the data in the learning process in order to enhance the performance. However, there is no existing study to demonstrate all possible scenarios where introducing topological properties can boost or harm the performance. This paper performs a detailed analysis of the effectiveness of topological properties for image classification in various training scenarios, defined by: the number of training samples, the complexity of the training data and the complexity of the backbone network. We identify the scenarios that benefit the most from topological features, e.g., training simple networks on small datasets. Additionally, we discuss the problem of topological consistency of the datasets which is one of the major bottlenecks for using topological features for classification. We further demonstrate how the topological inconsistency can harm the performance for certain scenarios.} }
Endnote
%0 Conference Paper %T Rethinking Persistent Homology For Visual Recognition %A Ekaterina Khramtsova %A Guido Zuccon %A Xi Wang %A Mahsa Baktashmotlagh %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-khramtsova22a %I PMLR %P 206--215 %U https://proceedings.mlr.press/v196/khramtsova22a.html %V 196 %X Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing research in this area focuses primarily on efficiently integrating topological properties of the data in the learning process in order to enhance the performance. However, there is no existing study to demonstrate all possible scenarios where introducing topological properties can boost or harm the performance. This paper performs a detailed analysis of the effectiveness of topological properties for image classification in various training scenarios, defined by: the number of training samples, the complexity of the training data and the complexity of the backbone network. We identify the scenarios that benefit the most from topological features, e.g., training simple networks on small datasets. Additionally, we discuss the problem of topological consistency of the datasets which is one of the major bottlenecks for using topological features for classification. We further demonstrate how the topological inconsistency can harm the performance for certain scenarios.
APA
Khramtsova, E., Zuccon, G., Wang, X. & Baktashmotlagh, M.. (2022). Rethinking Persistent Homology For Visual Recognition. Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:206-215 Available from https://proceedings.mlr.press/v196/khramtsova22a.html.

Related Material