上海市医学图像处理与计算机辅助手术重点实验室

上海市医学图像处理与计算机辅助手术重点实验室

    • 复旦大学上海医学院-上海市医学图像处理与计算机辅助手术重点实验室-外观图
    • 复旦大学-博学而笃志,切问而近思
    • 复旦大学上海医学院-上海市医学图像处理与计算机辅助手术重点实验室

    优秀论文

    [Frontiers of Computer Science] A Learnable Self-Supervised Task for Unsupervised Domain Adaptation on Point Cloud Classification and Segmentation

    发表时间:2022-12-03

    A Learnable Self-Supervised Task for Unsupervised Domain Adaptation on Point Cloud Classification and Segmentation

    Shaolei Liu*, Xiaoyuan Luo*, Kexue Fu, ManningWang, Zhijian Song

    Frontiers of Computer Science (CCF-B, IF=2.061)

    To address the UDA problem for point clouds, we propose a novel learnable self-supervised task that helps the adapted neural network extract transferable features. Specifically, we propose a learnable point cloud transformation and use it in a point cloud destruction-reconstruction self-supervised auxiliary task. We train the main task network and the auxiliary task network, which share an encoder, so that the encoder extracts feature that are highly transferable to the target domain. We further propose a multi-region transformation strategy to make the network focus on local features, which are more transferable. New state-of-the-art performance is achieved on the point cloud classification and segmentation UDA benchmarks.