A multi-label convolutional neural network for automatic image annotation

Alexis Vallet, Hiroyasu Sakamoto

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

Over the past few years, convolutional neural networks (CNN) have set the state of the art in a wide variety of supervised computer vision problems. Most research effort has focused on single-label classification, due to the availability of the large scale ImageNet dataset. Via pre-training on this dataset, CNNs have also shown the ability to outperform traditional methods for multi-label classification. Such methods, however, typically require evaluating many expensive forward passes to produce a multi-label distribution. Furthermore, due to the lack of a large scale multi-label dataset, little effort has been invested into training CNNs from scratch with multi-label data. In this paper, we address both issues by introducing a multi-label cost function adequate for deep CNNs, and a prediction method requiring only a single forward pass to produce multi-label predictions. We show the performance of our method on a newly introduced large scale multi-label dataset of animation images. Here, our method reaches 75.1% precision and 66.5% accuracy, making it suitable for automated annotation in practice. Additionally, we apply our method to the Pascal VOC 2007 dataset of natural images, and show that our prediction method outperforms a comparable model for a fraction of the computational cost.

Original languageEnglish
Pages (from-to)767-775
Number of pages9
JournalJournal of information processing
Volume23
Issue number6
DOIs
Publication statusPublished - Nov 15 2015

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'A multi-label convolutional neural network for automatic image annotation'. Together they form a unique fingerprint.

Cite this