Corpus ID: 212644710

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class

  title={Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class},
  author={Xi Li and Huimin Ma and Sheng Yi and Y. Chen},
  • Xi Li, Huimin Ma, +1 author Y. Chen
  • Published 2020
  • Computer Science
  • ArXiv
  • Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have achieved acceptable performance. However, when facing complex scenes, since image contains a large amount of classes, it becomes difficult to learn visual appearance based on image tags. In this case, image-level annotations are not effective in providing… CONTINUE READING

    Figures, Tables, and Topics from this paper


    Weaklier Supervised Semantic Segmentation With Only One Image Level Annotation per Category
    • 3
    From image-level to pixel-level labeling with Convolutional Networks
    • 432
    • PDF
    STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
    • 309
    • PDF
    Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation
    • Jiwoon Ahn, Suha Kwak
    • Computer Science
    • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    • 2018
    • 142
    • Highly Influential
    • PDF
    Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
    • 384
    • PDF
    FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference
    • 85
    • PDF
    Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
    • 108
    • PDF
    BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
    • Jifeng Dai, Kaiming He, Jian Sun
    • Computer Science
    • 2015 IEEE International Conference on Computer Vision (ICCV)
    • 2015
    • 543
    • PDF