PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912100245307392 |
|---|---|
| author | Jiang, Jincen Zhou, Qianyu Li, Yuhang Zhao, Xinkui Wang, Meili Ma, Lizhuang Chang, Jian Zhang, Jian Jun Lu, Xuequan |
| author_facet | Jiang, Jincen Zhou, Qianyu Li, Yuhang Zhao, Xinkui Wang, Meili Ma, Lizhuang Chang, Jian Zhang, Jian Jun Lu, Xuequan |
| contents | In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain. We introduce a multi-task setting for PCoTTA, which is practical and realistic, handling multiple tasks within one unified model during the continual adaptation. Our PCoTTA involves three key components: automatic prototype mixture (APM), Gaussian Splatted feature shifting (GSFS), and contrastive prototype repulsion (CPR). Firstly, APM is designed to automatically mix the source prototypes with the learnable prototypes with a similarity balancing factor, avoiding catastrophic forgetting. Then, GSFS dynamically shifts the testing sample toward the source domain, mitigating error accumulation in an online manner. In addition, CPR is proposed to pull the nearest learnable prototype close to the testing feature and push it away from other prototypes, making each prototype distinguishable during the adaptation. Experimental comparisons lead to a new benchmark, demonstrating PCoTTA's superiority in boosting the model's transferability towards the continually changing target domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00632 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding Jiang, Jincen Zhou, Qianyu Li, Yuhang Zhao, Xinkui Wang, Meili Ma, Lizhuang Chang, Jian Zhang, Jian Jun Lu, Xuequan Computer Vision and Pattern Recognition Machine Learning In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain. We introduce a multi-task setting for PCoTTA, which is practical and realistic, handling multiple tasks within one unified model during the continual adaptation. Our PCoTTA involves three key components: automatic prototype mixture (APM), Gaussian Splatted feature shifting (GSFS), and contrastive prototype repulsion (CPR). Firstly, APM is designed to automatically mix the source prototypes with the learnable prototypes with a similarity balancing factor, avoiding catastrophic forgetting. Then, GSFS dynamically shifts the testing sample toward the source domain, mitigating error accumulation in an online manner. In addition, CPR is proposed to pull the nearest learnable prototype close to the testing feature and push it away from other prototypes, making each prototype distinguishable during the adaptation. Experimental comparisons lead to a new benchmark, demonstrating PCoTTA's superiority in boosting the model's transferability towards the continually changing target domain. |
| title | PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.00632 |