Fine-Grained Image Retrieval via Piecewise Cross Entropy loss

作者：

Highlights：

• Fine-Grained Image Retrieval is an important problem in computer vision.

• In this paper, PCE loss is proposed for Fine-Grained Image Retrieval.

• Due to the proposed loss, our model obtains SOTA performances on two benchmarks.

摘要

•Fine-Grained Image Retrieval is an important problem in computer vision.•In this paper, PCE loss is proposed for Fine-Grained Image Retrieval.•Due to the proposed loss, our model obtains SOTA performances on two benchmarks.

论文关键词：Fine-Grained Image Retrieval,CNN,Piecewise cross entropy loss

论文评审过程：Received 14 October 2019, Accepted 20 October 2019, Available online 1 November 2019, Version of Record 21 January 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.10.006