Saved in:
Bibliographic Details
Main Authors: Jeon, Eun Som, Khurana, Rahul, Pathak, Aishani, Turaga, Pavan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.05316
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929412896718848
author Jeon, Eun Som
Khurana, Rahul
Pathak, Aishani
Turaga, Pavan
author_facet Jeon, Eun Som
Khurana, Rahul
Pathak, Aishani
Turaga, Pavan
contents Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very difficult. To this end, topological data analysis (TDA) has been utilized to derive useful representations that can contribute to improving performance and robustness against perturbations. Despite its effectiveness, the requirements for large computational resources and significant time consumption in extracting topological features through TDA are critical problems when implementing it on small devices. To address this issue, we propose a framework called Topological Guidance-based Knowledge Distillation (TGD), which uses topological features in knowledge distillation (KD) for image classification tasks. We utilize KD to train a superior lightweight model and provide topological features with multiple teachers simultaneously. We introduce a mechanism for integrating features from different teachers and reducing the knowledge gap between teachers and the student, which aids in improving performance. We demonstrate the effectiveness of our approach through diverse empirical evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05316
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging Topological Guidance for Improved Knowledge Distillation
Jeon, Eun Som
Khurana, Rahul
Pathak, Aishani
Turaga, Pavan
Computer Vision and Pattern Recognition
Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very difficult. To this end, topological data analysis (TDA) has been utilized to derive useful representations that can contribute to improving performance and robustness against perturbations. Despite its effectiveness, the requirements for large computational resources and significant time consumption in extracting topological features through TDA are critical problems when implementing it on small devices. To address this issue, we propose a framework called Topological Guidance-based Knowledge Distillation (TGD), which uses topological features in knowledge distillation (KD) for image classification tasks. We utilize KD to train a superior lightweight model and provide topological features with multiple teachers simultaneously. We introduce a mechanism for integrating features from different teachers and reducing the knowledge gap between teachers and the student, which aids in improving performance. We demonstrate the effectiveness of our approach through diverse empirical evaluations.
title Leveraging Topological Guidance for Improved Knowledge Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.05316