In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection tasks tackle this complexity by operating in a cascaded fashion: they first extract a 2D bounding box based on which additional attributes, e.g. instance masks, are inferred. While these methods perform well, a key challenge remains the lack of accurate and cheap annotations for the growing variety of tasks. Synthetic data presents a promising solution but, despite the effort in domain adaptation research, the gap between synthetic and real data remains an open problem. In this work, we propose a weakly supervised domain adaptation setting which exploits the structure of cascaded detection tasks. In particular, we learn to infer the attributes solely from the source domain while leveraging 2D bounding boxes as weak labels in both domains to explain the domain shift. We further encourage domain-invariant features through class-wise feature alignment using ground-truth class information, which is not available in the unsupervised setting. As our experiments demonstrate, the approach is competitive with fully supervised settings while outperforming unsupervised adaptation approaches by a large margin.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation


    Contributors:


    Publication date :

    2021-07-11


    Size :

    3370058 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Weakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition

    Zhu, F. / Shao, L. | British Library Online Contents | 2014


    Weakly-Supervised Crack Detection

    Inoue, Yuki / Nagayoshi, Hiroto | IEEE | 2023


    Improving Cross-Domain Semi-Supervised Object Detection with Adversarial Domain Adaptation

    Menke, Maximilian / Wenzel, Thomas / Schwung, Andreas | IEEE | 2023


    Weakly supervised learning of actions from transcripts

    Kuehne, Hilde / Richard, Alexander / Gall, Juergen | British Library Online Contents | 2017


    Weakly Supervised Localization and Learning with Generic Knowledge

    Deselaers, T. / Alexe, B. / Ferrari, V. | British Library Online Contents | 2012