跳到主要导航 跳到搜索 跳到主要内容

Zigzag Learning for Weakly Supervised Object Detection

  • National University of Singapore
  • Shanghai Jiao Tong University
  • University of Texas at San Antonio

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums due to the introduced false positive examples. Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds. Towards this goal, we first develop a criterion named mean Energy Accumulation Scores (mEAS) to automatically measure and rank localization difficulty of an image containing the target object, and accordingly learn the detector progressively by feeding examples with increasing difficulty. In this way, the model can be well prepared by training on easy examples for learning from more difficult ones and thus gain a stronger detection ability more efficiently. Furthermore, we introduce a novel masking regularization strategy over the high level convolutional feature maps to avoid overfitting initial samples. These two modules formulate a zigzag learning process, where progressive learning endeavors to discover reliable object instances, and masking regularization increases the difficulty of finding object instances properly. We achieve 47.6% mAP on PASCAL VOC 2007, surpassing the state-of-the-arts by a large margin.

源语言英语
主期刊名Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
出版商IEEE Computer Society
页4262-4270
页数9
ISBN(电子版)9781538664209
DOI
出版状态已出版 - 14 12月 2018
已对外发布是
活动31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, 美国
期限: 18 6月 2018 → 22 6月 2018

丛书

姓名Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN(印刷版)1063-6919

会议

会议31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
国家/地区美国
市Salt Lake City
时期18/06/18 → 22/06/18

学术指纹

探究 'Zigzag Learning for Weakly Supervised Object Detection' 的科研主题。它们共同构成独一无二的学术指纹。

引用此