Is object localization for free? - Weakly-supervised learning with convolutional neural networks
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2015)
摘要
Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object bounding boxes, however, is both expensive and often subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects. We quantify its object classification and object location prediction performance on the Pascal VOC 2012 (20 object classes) and the much larger Microsoft COCO (80 object classes) datasets. We find that the network (i) outputs accurate image-level labels, (ii) predicts approximate locations (but not extents) of objects, and (iii) performs comparably to its fully-supervised counterparts using object bounding box annotation for training.
更多查看译文
关键词
object localization,weakly-supervised learning,convolutional neural networks,visual object recognition,image annotation,CNN,object classification,object location prediction performance,Pascal VOC dataset,Microsoft COCO dataset,image-level labels,object bounding box annotation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络