TY - GEN
T1 - GENERATION FOR UNSUPERVISED DOMAIN ADAPTATION
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
AU - Huang, Junxuan
AU - Yuan, Junsong
AU - Qiao, Chunming
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - Recent deep networks have achieved good performance on a variety of 3d points classification tasks. However, these models often face challenges in “wild tasks” where there are considerable differences between the labeled training/source data collected by one Lidar and unseen test/target data collected by a different Lidar. Unsupervised domain adaptation (UDA) seeks to overcome such a problem without target domain labels. Instead of aligning features between source data and target data, we propose a method that uses a Generative Adversarial Network (GAN) to generate synthetic data from the source domain so that the output is close to the target domain. Experiments show that our approach performs better than state-of-the-art UDA methods in three popular 3D object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3D object classification.
AB - Recent deep networks have achieved good performance on a variety of 3d points classification tasks. However, these models often face challenges in “wild tasks” where there are considerable differences between the labeled training/source data collected by one Lidar and unseen test/target data collected by a different Lidar. Unsupervised domain adaptation (UDA) seeks to overcome such a problem without target domain labels. Instead of aligning features between source data and target data, we propose a method that uses a Generative Adversarial Network (GAN) to generate synthetic data from the source domain so that the output is close to the target domain. Experiments show that our approach performs better than state-of-the-art UDA methods in three popular 3D object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3D object classification.
KW - 3D object classification
KW - GAN
KW - Unsupervised domain adaptation
UR - https://www.scopus.com/pages/publications/85131247573
U2 - 10.1109/ICASSP43922.2022.9746185
DO - 10.1109/ICASSP43922.2022.9746185
M3 - Conference contribution
AN - SCOPUS:85131247573
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3753
EP - 3757
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 May 2022 through 27 May 2022
ER -