Simplified Learning of CAD Features Leveraging a Deep Residual Autoencoder

TL;DR

This paper introduces a deep residual 3D autoencoder based on EfficientNet architecture, designed to improve transfer learning for CAD model assessment by reducing the need for labeled data in 3D computer vision tasks.

Contribution

It presents a novel 3D autoencoder leveraging EfficientNet for transfer learning in CAD model analysis, addressing data scarcity issues.

Findings

Effective in reducing labeled data requirements

Applicable to voxel models from STEP files

Enhances transfer learning in 3D CAD assessment

Abstract

In the domain of computer vision, deep residual neural networks like EfficientNet have set new standards in terms of robustness and accuracy. One key problem underlying the training of deep neural networks is the immanent lack of a sufficient amount of training data. The problem worsens especially if labels cannot be generated automatically, but have to be annotated manually. This challenge occurs for instance if expert knowledge related to 3D parts should be externalized based on example models. One way to reduce the necessary amount of labeled data may be the use of autoencoders, which can be learned in an unsupervised fashion without labeled data. In this work, we present a deep residual 3D autoencoder based on the EfficientNet architecture, intended for transfer learning tasks related to 3D CAD model assessment. For this purpose, we adopted EfficientNet to 3D problems like voxel models derived from a STEP file. Striving to reduce the amount of labeled 3D data required, the networks encoder can be utilized for transfer training.