Saliency for fine-grained object recognition in domains with scarce training data

作者：

Highlights：

• We investigated the role of saliency on improving the classification accuracy when the training data is scarce.

• We considered adding a saliency branch to an existing CNN architecture (AlexNet, ResNet-50 and ResNet-152).

• We validated our approach on the fine-grained object recognition problem.

• Experimental results confirmed that our approach is useful for the case when the available training data is scarce.

• Our experiments show that there exists a clear correlation (Pearson coefficient) between the performance of saliency methods on standard saliency benchmarks and the performance gain that is obtained when incorporating them in a object recognition pipeline.

摘要

•We investigated the role of saliency on improving the classification accuracy when the training data is scarce.•We considered adding a saliency branch to an existing CNN architecture (AlexNet, ResNet-50 and ResNet-152).•We validated our approach on the fine-grained object recognition problem.•Experimental results confirmed that our approach is useful for the case when the available training data is scarce.•Our experiments show that there exists a clear correlation (Pearson coefficient) between the performance of saliency methods on standard saliency benchmarks and the performance gain that is obtained when incorporating them in a object recognition pipeline.

论文关键词：Object recognition,Fine-grained classification,Saliency detection,Scarce training data

论文评审过程：Received 10 July 2018, Revised 25 April 2019, Accepted 1 May 2019, Available online 4 May 2019, Version of Record 21 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.002