51. Weakly- and Semi-supervised Faster R-CNN with Curriculum Learning
- Author
-
Xinggang Wang, Jiasi Wang, and Wenyu Liu
- Subjects
Training set ,business.industry ,Computer science ,Feature extraction ,Detector ,Pattern recognition ,02 engineering and technology ,Pascal (programming language) ,010501 environmental sciences ,01 natural sciences ,Object detection ,Minimum bounding box ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,Curriculum ,0105 earth and related environmental sciences ,computer.programming_language - Abstract
Object detection is a core problem in computer vision and pattern recognition. In this paper, we study the problem of learning an effective object detector using weakly-annotated images (i.e., only the image level annotation is given) and a small proportion of fully-annotated images (i.e., bounding box level annotation is given) with curriculum learning. Our method is built upon Faster R-CNN. Different from previous weakly-supervised object detectors which rely on hand-craft object proposals, the proposed method learns a region proposal network using weakly- and semi-supervised training data. And the weakly-labeled images are fed into the deep network in a meaningful order which illustrates from easy to gradually more complex examples with curriculum learning. We name the Faster R-CNN trained using Weakly- And Semi-Supervised data with Curriculum Learning as WASSCL R-CNN. The WASSCL R-CNN is validated on the PASCAL VOC 2007 benchmark, and obtains 90% of a fully-supervised Faster R-CNN's performance (measured using mAP) with only 15% of fully-supervised annotations together with weak supervision. The results show that the proposed learning framework can significantly reduce the labeling efforts for obtaining reliable object detectors.
- Published
- 2018