Evaluating Deep Clustering Algorithms on Non-Categorical 3D CAD Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911859713507328 |
|---|---|
| author | Xiang, Siyuan Tseng, Chin Wen, Congcong Desai, Deshana Kou, Yifeng Starly, Binil Panozzo, Daniele Feng, Chen |
| author_facet | Xiang, Siyuan Tseng, Chin Wen, Congcong Desai, Deshana Kou, Yifeng Starly, Binil Panozzo, Daniele Feng, Chen |
| contents | We introduce the first work on benchmarking and evaluating deep clustering algorithms on large-scale non-categorical 3D CAD models. We first propose a workflow to allow expert mechanical engineers to efficiently annotate 252,648 carefully sampled pairwise CAD model similarities, from a subset of the ABC dataset with 22,968 shapes. Using seven baseline deep clustering methods, we then investigate the fundamental challenges of evaluating clustering methods for non-categorical data. Based on these challenges, we propose a novel and viable ensemble-based clustering comparison approach. This work is the first to directly target the underexplored area of deep clustering algorithms for 3D shapes, and we believe it will be an important building block to analyze and utilize the massive 3D shape collections that are starting to appear in deep geometric computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19134 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Deep Clustering Algorithms on Non-Categorical 3D CAD Models Xiang, Siyuan Tseng, Chin Wen, Congcong Desai, Deshana Kou, Yifeng Starly, Binil Panozzo, Daniele Feng, Chen Computer Vision and Pattern Recognition We introduce the first work on benchmarking and evaluating deep clustering algorithms on large-scale non-categorical 3D CAD models. We first propose a workflow to allow expert mechanical engineers to efficiently annotate 252,648 carefully sampled pairwise CAD model similarities, from a subset of the ABC dataset with 22,968 shapes. Using seven baseline deep clustering methods, we then investigate the fundamental challenges of evaluating clustering methods for non-categorical data. Based on these challenges, we propose a novel and viable ensemble-based clustering comparison approach. This work is the first to directly target the underexplored area of deep clustering algorithms for 3D shapes, and we believe it will be an important building block to analyze and utilize the massive 3D shape collections that are starting to appear in deep geometric computing. |
| title | Evaluating Deep Clustering Algorithms on Non-Categorical 3D CAD Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.19134 |