Learning Deep Features for Discriminative Localization
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2016)
摘要
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on imagelevel labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that exposes the implicit attention of CNNs on an image. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014 without training on any bounding box annotation. We demonstrate in a variety of experiments that our network is able to localize the discriminative image regions despite just being trained for solving classification task1.
更多查看译文
关键词
deep feature learning,discriminative localization,global average pooling layer,convolutional neural network,localizable deep representation,CNN,object localization,classification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络