Corpus ID: 221266049

Robust Vision Challenge 2020 - 1st Place Report for Panoptic Segmentation

  title={Robust Vision Challenge 2020 - 1st Place Report for Panoptic Segmentation},
  author={R. Mohan and Abhinav Valada},
  • R. Mohan, Abhinav Valada
  • Published 2020
  • Computer Science
  • ArXiv
  • In this technical report, we present key details of our winning panoptic segmentation architecture EffPS b1bs4 RVC. Our network is a lightweight version of our state-of-the-art EfficientPS architecture that consists of our proposed shared backbone with a modified EfficientNet-B5 model as the encoder, followed by the 2-way FPN to learn semantically rich multi-scale features. It consists of two task-specific heads, a modified Mask R-CNN instance head and our novel semantic segmentation head that… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Panoptic Segmentation
    • 177
    • PDF
    EfficientPS: Efficient Panoptic Segmentation
    • 4
    • PDF
    Microsoft COCO: Common Objects in Context
    • 10,263
    • Highly Influential
    • PDF
    The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
    • 311
    • PDF
    The Cityscapes Dataset for Semantic Urban Scene Understanding
    • 3,242
    • Highly Influential
    • PDF
    Squeeze-and-Excitation Networks
    • 2,211
    • PDF
    Object scene flow for autonomous vehicles
    • 906
    • PDF
    EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
    • 892
    • PDF
    Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
    • 169
    • PDF