Learning multi-layer coarse-to-fine representations for large-scale image classification

作者：

Highlights：

• Inter-category visual and semantic correlations are exploited.

• Large numbers of structural image classes are organized hierarchically.

• Hierarchical multi-task SVMs are trained over the visual-semantic tree.

• The visual-semantic tree and CNNs are integrated as another framework.

• We perform our experiments on 10k image categories for algorithm evaluation.

摘要

•Inter-category visual and semantic correlations are exploited.•Large numbers of structural image classes are organized hierarchically.•Hierarchical multi-task SVMs are trained over the visual-semantic tree.•The visual-semantic tree and CNNs are integrated as another framework.•We perform our experiments on 10k image categories for algorithm evaluation.

论文关键词：Visual-semantic tree,Inter-category correlation,Multi-task learning,Deep convolutional neural network,Large-scale image classification

论文评审过程：Received 22 February 2018, Revised 21 December 2018, Accepted 22 February 2019, Available online 23 February 2019, Version of Record 28 February 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.02.024