OCEAN: Object-centric arranging network for self-supervised visual representations learning

作者：

Highlights：

• A self-supervised learning which does not require human annotations for training CNN.

• Learning the correct arrangement of object proposals to represent an image by CNN.

• Demonstrating the advantage of our model by applying it to PASCAL VOC datasets.

• Application to other vision tasks including image retrieval and semantic matching.

摘要

•A self-supervised learning which does not require human annotations for training CNN.•Learning the correct arrangement of object proposals to represent an image by CNN.•Demonstrating the advantage of our model by applying it to PASCAL VOC datasets.•Application to other vision tasks including image retrieval and semantic matching.

论文关键词：Self-supervised learning,Visual representations learning,Object proposals,Convolutional neural networks

论文评审过程：Received 16 May 2018, Revised 21 January 2019, Accepted 29 January 2019, Available online 6 February 2019, Version of Record 12 February 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.073