autogpart.github.io - AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation

Description: AutoGPart searches for intermediate supervisions automatically for a part segmentation network to increase its generalizability.

automl (16) part segmentation (1) intermediate supervision (1)

Example domain paragraphs

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

AutoGPart searches for intermediate supervisions for a generalizable 3D part segmentation network. By training the network with searched features encoding correct part cues, the network could perform better when parsing an instance from a novel distribution.

AutoGPart builds an intermediate supervision space based on prior knowledge of 3D segmentation tasks. The space contains all operations to generate supervision features from input geometry features and ground-truth labels. Then, we optimize the supervision space to fit it to a given part segmentation network via a ``propose, evaluate, and update'' approach. In each update cycle, an operation is first sampled to generate supervision features for each point in the shape. Then, it is evaluated by training the

Links to autogpart.github.io (4)

ericyi.github.io Li Yi
xxm19.github.io Xiaomeng Xu
meowuu7.github.io Xueyi Liu
equi-articulated-pose.github.io Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance