论文阅读 [CVPR-2022] AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

论文阅读 [CVPR-2022] AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

studyai.com

搜索论文: AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

http://www.studyai.com/search/whole-site/?q=AutoGPart+Intermediate+Supervision+Search+for+Generalizable+3D+Part+Segmentation

摘要(Abstract)

Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications.

训练一个通用的三维零件分割网络是一个非常具有挑战性的问题，但在实际应用中非常重要。

To tackle this problem, some works design task-specific solutions by translating human understanding of the task to machine’s learning process, which faces the risk of missing the optimal strategy since machines do not necessarily understand in the exact human way.

为了解决这个问题，一些作品通过将人类对任务的理解转化为机器的学习过程来设计特定于任务的解决方案，机器的学习过程面临着错过最佳策略的风险，因为机器不一定以精确的人类方式理解。

Others try to use conventional task-agnostic approaches designed for domain generalization problems with no task prior knowledge considered.

其他人则尝试使用传统的任务不可知方法来解决领域泛化问题，而不考虑任务先验知识。

To solve the above issues, we propose AutoGPart, a generic method enabling training generalizable 3D part segmentation networks with the task prior considered.

为了解决上述问题，我们提出了AutoGPart，这是一种通用的方法，可以在考虑任务的情况下训练通用的三维零件分割网络。

AutoGPart builds a supervision space with geometric prior knowledge encoded, and lets the machine to search for the optimal supervisions from the space for a specific segmentation task automatically.

AutoGPart用编码的几何先验知识构建监督空间，并允许机器自动从空间中搜索特定分割任务的最优监督。

Extensive experiments on three generalizable 3D part segmentation tasks are conducted to demonstrate the effectiveness and versatility of AutoGPart.

在三个通用的三维零件分割任务上进行了大量实验，以证明AutoGPart的有效性和通用性。

We demonstrate that the performance of segmentation networks using simple backbones can be significantly improved when trained with supervisions searched by our method.

我们证明了使用简单主干的分割网络的性能在使用我们的方法搜索的监督进行训练时可以显著提高。