AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

03/13/2022
by   Xueyi Liu, et al.
0

Training a generalizable 3D part segmentation network is quite challenging but of great importance in real-world applications. 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. Others try to use conventional task-agnostic approaches designed for domain generalization problems with no task prior knowledge considered. To solve the above issues, we propose AutoGPart, a generic method enabling training generalizable 3D part segmentation networks with the task prior considered. 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. Extensive experiments on three generalizable 3D part segmentation tasks are conducted to demonstrate the effectiveness and versatility of AutoGPart. We demonstrate that the performance of segmentation networks using simple backbones can be significantly improved when trained with supervisions searched by our method.

READ FULL TEXT
research
10/08/2021

3D Meta-Segmentation Neural Network

Though deep learning methods have shown great success in 3D point cloud ...
research
10/04/2019

A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology

We introduce a method for training neural networks to perform image or v...
research
02/18/2020

KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge

Reinforcement learning agents usually learn from scratch, which requires...
research
02/22/2021

Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks

We study the problem of incorporating prior knowledge into a deep Transf...
research
09/12/2019

Unsupervised Learning and Exploration of Reachable Outcome Space

Performing Reinforcement Learning in sparse rewards settings, with very ...
research
06/17/2022

The Importance of Background Information for Out of Distribution Generalization

Domain generalization in medical image classification is an important pr...

Please sign up or login with your details

Forgot password? Click here to reset