Towards Multi-source Adaptive Semantic Segmentation

被引:17
作者
Russo, Paolo [1 ,2 ]
Tommasi, Tatiana [3 ]
Caputo, Barbara [1 ,3 ]
机构
[1] Ist Italiano Tecnol, Genoa, Italy
[2] Sapienza Univ Roma, Rome, Italy
[3] Politecn Torino, Turin, Italy
来源
IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT I | 2019年 / 11751卷
关键词
Semantic segmentation; Domain adaptation;
D O I
10.1007/978-3-030-30642-7_26
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
When applying powerful deep learning approaches on real world tasks like pixel level annotation of urban scenes it becomes clear that even those strong learners may fail dramatically and are still not ready for deployment in the wild. For semantic segmentation, one of the main practical challenges consists in finding large annotated collection to feed the data hungry networks. Synthetic images in combination with adaptive learning models have shown to help with this issue, but in general, different synthetic sources are analyzed separately, not leveraging on the potential growth in data amount and sample variability that could result from their combination. With our work we investigate for the first time the multi-source adaptive semantic segmentation setting, proposing some best practice rule for the data and model integration. Moreover we show how to extend an existing semantic segmentation approach to deal with multiple sources obtaining promising results.
引用
收藏
页码:292 / 301
页数:10
相关论文
共 29 条
  • [1] [Anonymous], 2016, PARSENET LOOKING WID
  • [2] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    Chen, Liang-Chieh
    Papandreou, George
    Kokkinos, Iasonas
    Murphy, Kevin
    Yuille, Alan L.
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) : 834 - 848
  • [3] Chen YH, 2017, AIP CONF PROC, V1812, DOI [10.1063/1.4975898, 10.1109/ICCV.2017.137]
  • [4] The Cityscapes Dataset for Semantic Urban Scene Understanding
    Cordts, Marius
    Omran, Mohamed
    Ramos, Sebastian
    Rehfeld, Timo
    Enzweiler, Markus
    Benenson, Rodrigo
    Franke, Uwe
    Roth, Stefan
    Schiele, Bernt
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3213 - 3223
  • [5] Dosovitskiy A., 2017, C ROBOT LEARNING, P1, DOI DOI 10.48550/ARXIV.1711.03938
  • [6] Duan L., 2009, Domain adaptation from multiple sources via auxiliary classifiers
  • [7] Domain Adaptation from Multiple Sources: A Domain-Dependent Regularization Approach
    Duan, Lixin
    Xu, Dong
    Tsang, Ivor Wai-Hung
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (03) : 504 - 518
  • [8] Hoffman J., 2018, ICML
  • [9] Simple Does It: Weakly Supervised Instance and Semantic Segmentation
    Khoreva, Anna
    Benenson, Rodrigo
    Hosang, Jan
    Hein, Matthias
    Schiele, Bernt
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1665 - 1674
  • [10] ImageNet Classification with Deep Convolutional Neural Networks
    Krizhevsky, Alex
    Sutskever, Ilya
    Hinton, Geoffrey E.
    [J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90