论文学习
Domain Adaptive Faster R-CNN for Object Detection in the Wild

发布于44个月以前

  • 0
  • 0
  • 181

发布于44个月以前

Domain Adaptive Faster R-CNN for Object Detection in the Wild

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination,etc., and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory,and are implemented by learning a domain classifier in ad versarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal net work (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

论文下载

论文地址:https://arxiv.org/pdf/1803.03243

算法链接

算法https://marketplace.huaweicloud.com/markets/aihub/modelhub/detail/?id=aafadaed-1419-4e5e-bdcf-23dbf3e030cb

算法指南

算法指南https://bbs.huaweicloud.com/forum/forum.php?mod=viewthread&tid=91218&page=1&extra=#pid515639

评论 0

登录后评论

    hyx

    作者相关内容

    2021无人车挑战杯baseline:使用自定义算法训练目标检测模型
    发布于44个月以前
    爱(AI)美食-图片分类ResNet算法实战baseline
    发布于44个月以前
    Deepjdot for Unsupervised Domain Adaptation
    发布于44个月以前
    Learn to Adapt Structured Output Space for Semantic Segmentation
    发布于44个月以前
    Domain Adaptive Faster R-CNN for Object Detection in the Wild
    发布于44个月以前

    暂无数据

    热门内容推荐

    快速体验10个精选论文复现算法模型,赢取蓝牙音箱、体脂秤、ModelArts图书!
    WAYNE 发布于44个月以前
    华为云AI论文精读会2021第二十期:轻量化神经网络MobileNet系列论文精读
    euuufe 发布于41个月以前
    [华为云AI经典论文复现] AI Gallery CrowdDet算法使用介绍
    euuufe 发布于42个月以前
    Fast-SCNN: Fast Semantic Segmentation Network
    spy 发布于44个月以前
    华为云AI论文精读会2021第四期:Dynamic RCNN:一种有效提升RCNN系列网络表现的动态训练方法
    euuufe 发布于42个月以前

    暂无数据