Positional Prompt Tuning for Efficient 3D Representation Learning
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_ | 1866908556016484352 |
|---|---|
| author | Zhang, Shaochen Qi, Zekun Dong, Runpei Bai, Xiuxiu Wei, Xing |
| author_facet | Zhang, Shaochen Qi, Zekun Dong, Runpei Bai, Xiuxiu Wei, Xing |
| contents | We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we explore parameter-efficient fine-tuning (PEFT) through the lens of prompts and adapters, introducing a straightforward yet effective method called PPT for point cloud analysis. PPT incorporates increased patch tokens and trainable positional encoding while keeping most pre-trained model parameters frozen. Extensive experiments validate that PPT is both effective and efficient. Our proposed method of PEFT tasks, namely PPT, with only 1.05M of parameters for training, gets state-of-the-art results in several mainstream datasets, such as 95.01% accuracy in the ScanObjectNN OBJ_BG dataset. Codes and weights will be released at https://github.com/zsc000722/PPT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11567 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Positional Prompt Tuning for Efficient 3D Representation Learning Zhang, Shaochen Qi, Zekun Dong, Runpei Bai, Xiuxiu Wei, Xing Computer Vision and Pattern Recognition We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we explore parameter-efficient fine-tuning (PEFT) through the lens of prompts and adapters, introducing a straightforward yet effective method called PPT for point cloud analysis. PPT incorporates increased patch tokens and trainable positional encoding while keeping most pre-trained model parameters frozen. Extensive experiments validate that PPT is both effective and efficient. Our proposed method of PEFT tasks, namely PPT, with only 1.05M of parameters for training, gets state-of-the-art results in several mainstream datasets, such as 95.01% accuracy in the ScanObjectNN OBJ_BG dataset. Codes and weights will be released at https://github.com/zsc000722/PPT. |
| title | Positional Prompt Tuning for Efficient 3D Representation Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.11567 |