Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval

Authors

  • Rui Xu Nanjing University of Science and Technology
  • Zongyan Han Nanjing University of Science and Technology
  • Le Hui Nanjing University of Science and Technology
  • Jianjun Qian Nanjing University of Science and Technology
  • Jin Xie Nanjing University of Science and Technology

DOI:

https://doi.org/10.1609/aaai.v36i3.20195

Keywords:

Computer Vision (CV)

Abstract

Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively recognize the categories that have not been used during training. In this paper, we propose a novel domain disentangled generative adversarial network (DD-GAN) for zero-shot sketch-based 3D retrieval, which can retrieve the unseen categories that are not accessed during training. Specifically, we first generate domain-invariant features and domain-specific features by disentangling the learned features of sketches and 3D shapes, where the domain-invariant features are used to align with the corresponding word embeddings. Then, we develop a generative adversarial network that combines the domain-specific features of the seen categories with the aligned domain-invariant features to synthesize samples, where the synthesized samples of the unseen categories are generated by using the corresponding word embeddings. Finally, we use the synthesized samples of the unseen categories combined with the real samples of the seen categories to train the network for retrieval, so that the unseen categories can be recognized. In order to reduce the domain shift problem, we utilize unlabeled unseen samples to enhance the discrimination ability of the discriminator. With the discriminator distinguishing the generated samples from the unlabeled unseen samples, the generator can generate more realistic unseen samples. Extensive experiments on the SHREC'13 and SHREC'14 datasets show that our method significantly improves the retrieval performance of the unseen categories.

Downloads

Published

2022-06-28

How to Cite

Xu, R., Han, Z., Hui, L., Qian, J., & Xie, J. (2022). Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 2902-2910. https://doi.org/10.1609/aaai.v36i3.20195

Issue

Section

AAAI Technical Track on Computer Vision III