Thema5126: Unterschied zwischen den Versionen
Mp3616 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Explainable Graph-based 3D Point Cloud Analysis |Vorname=Zhan |Nachname=Qu |Abschlussarbeitstyp=Bachelor, Master |Betreuer=Zhan Qu |Fo…“) |
Mp3616 (Diskussion | Beiträge) |
||
Zeile 7: | Zeile 7: | ||
|Forschungsgruppe=Web Science | |Forschungsgruppe=Web Science | ||
|Abschlussarbeitsstatus=Offen | |Abschlussarbeitsstatus=Offen | ||
− | |Beginn=2024/ | + | |Beginn=2024/01/16 |
|Ausschreibung=Thesis_Explainable3DPointCloudAnalysis.pdf | |Ausschreibung=Thesis_Explainable3DPointCloudAnalysis.pdf | ||
− | |Beschreibung DE= | + | |Beschreibung DE=The utilization of Point Cloud data has emerged as a pivotal component in the field of 3D object representation, finding relevance in various domains such as autonomous driving, robotics, drones, and augmented/virtual reality. Within the domain of 3D Point Cloud analysis, fundamental tasks include classification and segmentation. Numerous models have been developed to address these challenges, with Graph-based methods, such as Dynamic Graph Convolutional Neural Network (DGCNN) [1] and its variations, have achieved state-of-the-art performance. However, the lack of explainability limits their practical applicability [2]. |
− | The utilization of Point Cloud data has emerged as a pivotal component in the field of 3D object representation, finding relevance in various domains such as autonomous driving, robotics, drones, and augmented/virtual reality. Within the domain of 3D Point Cloud analysis, fundamental tasks include classification and segmentation. Numerous models have been developed to address these challenges, with Graph-based methods, such as Dynamic Graph Convolutional Neural Network (DGCNN) [1] and its variations, have achieved state-of-the-art performance. However, the lack of explainability limits their practical applicability [2]. | + | |
The principal aim of this thesis is to develop a novel method to enhance the explainability of Graph-based models for 3D Point Cloud Analysis. By undertaking this thesis, you will not only contribute to bridging the gap between cutting-edge 3D Point Cloud analysis techniques and Graph-based models, but also develop a deep understanding of how to use explainable AI to improve the trustworthiness and interpretability of Deep Neural Networks in real-world applications. | The principal aim of this thesis is to develop a novel method to enhance the explainability of Graph-based models for 3D Point Cloud Analysis. By undertaking this thesis, you will not only contribute to bridging the gap between cutting-edge 3D Point Cloud analysis techniques and Graph-based models, but also develop a deep understanding of how to use explainable AI to improve the trustworthiness and interpretability of Deep Neural Networks in real-world applications. | ||
− | + | ||
− | |||
− | |||
− | |||
− | |||
[1] DGCNN | [1] DGCNN | ||
[2] Point Cloud Saliency Maps | [2] Point Cloud Saliency Maps | ||
}} | }} |
Aktuelle Version vom 16. Januar 2024, 12:31 Uhr
Abschlussarbeitstyp: Bachelor, Master
Betreuer: Zhan Qu
Forschungsgruppe: Web Science
Archivierungsnummer: 5126
Abschlussarbeitsstatus: Offen
Beginn:
16. Januar 2024
Abgabe: unbekannt
The utilization of Point Cloud data has emerged as a pivotal component in the field of 3D object representation, finding relevance in various domains such as autonomous driving, robotics, drones, and augmented/virtual reality. Within the domain of 3D Point Cloud analysis, fundamental tasks include classification and segmentation. Numerous models have been developed to address these challenges, with Graph-based methods, such as Dynamic Graph Convolutional Neural Network (DGCNN) [1] and its variations, have achieved state-of-the-art performance. However, the lack of explainability limits their practical applicability [2].
The principal aim of this thesis is to develop a novel method to enhance the explainability of Graph-based models for 3D Point Cloud Analysis. By undertaking this thesis, you will not only contribute to bridging the gap between cutting-edge 3D Point Cloud analysis techniques and Graph-based models, but also develop a deep understanding of how to use explainable AI to improve the trustworthiness and interpretability of Deep Neural Networks in real-world applications.
[1] DGCNN
[2] Point Cloud Saliency Maps
Ausschreibung: Download (pdf)