Geographic Information Use In Weakly-Supervised Deep Learning For Landmark Recognition
2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)(2017)
摘要
The successful deep convolutional neural networks for visual object recognition typically rely on a massive number of training images that are well annotated by class labels or object bounding boxes with great human efforts. Here we explore the use of the geographic metadata, which are automatically retrieved from sensors such as GPS and compass, in weakly-supervised learning techniques for landmark recognition. The visibility of a landmark in a frame can be calculated based on the camera's field-of-view and the landmark's geometric information such as location and height. Subsequently, a training dataset is generated as the union of the frames with presence of at least one target landmark. To reduce the impact of the intrinsic noise in the geo-metadata, we present a frame selection method that removes the mistakenly labeled frames with a two-step approach consisting of (1) Gaussian Mixture Model clustering based on camera location followed by (2) outlier removal based on visual consistency. We compare the classification results obtained from the ground truth labels and the noisy labels derived from the raw geo-metadata. Experiments show that training based on the raw geo-metadata achieves a Mean Average Precision (MAP) of 0.797. Moreover, by applying our proposed representative frame selection method, the MAP can be further improved by 6.4%, which indicates the promising use of the geo-metadata in weakly-supervised learning techniques.
更多查看译文
关键词
mean average precision,MAP,noisy labels,ground truth labels,visual consistency,outlier removal,camera location,Gaussian mixture model clustering,frame selection method,geo-metadata,intrinsic noise,landmark height,landmark location,landmark geometric information,camera field-of-view,landmark visibility,geographic metadata,object bounding boxes,class labels,image annotation,training images,visual object recognition,deep convolutional neural networks,landmark recognition,weakly-supervised deep learning,geographic information
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络