Semantic Scholar Open Access 2015 10424 sitasi

Learning Deep Features for Discriminative Localization

Bolei Zhou A. Khosla Àgata Lapedriza A. Oliva A. Torralba

Lihat Sumber DOI

Abstrak

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.

Topik & Kata Kunci

Computer Science

Penulis (5)

Bolei Zhou

A. Khosla

Àgata Lapedriza

A. Oliva

A. Torralba

Format Sitasi

APA MLA BibTeX

Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A. (2015). Learning Deep Features for Discriminative Localization. https://doi.org/10.1109/CVPR.2016.319

Akses Cepat

Lihat di Sumber doi.org/10.1109/CVPR.2016.319

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Total Sitasi: 10424×
Sumber Database: Semantic Scholar
DOI: 10.1109/CVPR.2016.319
Akses: Open Access ✓