Refining deep convolutional features for improving fine-grained image recognition

EURASIP Journal on Image and Video Processing

Weixia Zhang¹  Jia Yan¹  Tianpeng Feng¹  Dexiang Deng¹  Wenxuan Shi² 

[1] School of Electronic Information, Wuhan University;School of Remote Sensing and Information Engineering, Wuhan University;

关键词: Fine-grained image recognition;    Convolutional Neural Networks (CNN);    Bag-of-visual-words;    Feature weighting;    Dimension reduction;   

DOI  :  10.1186/s13640-017-0176-3

来源: DOAJ

【 摘 要 】

Abstract Fine-grained image recognition, a computer vision task filled with challenges due to its imperceptible inter-class variance and large intra-class variance, has been drawing increasing attention. While manual annotation can be utilized to effectively enhance performance in this task, it is extremely time-consuming and expensive. Recently, Convolutional Neural Networks (CNN) achieved state-of-the-art performance in image classification. We propose a fine-grained image recognition framework by exploiting CNN as the raw feature extractor along with several effective methods including a feature encoding method, a feature weighting method, and a strategy to better incorporate information from multi-scale images to further improve recognition ability. Besides, we investigate two dimension reduction methods and successfully merge them to our framework to compact the final image representation. Based on the discriminative and compact framework, we achieved the state-of-the-art performance in terms of classification accuracy on several fine-grained image recognition benchmarks based on weekly supervision.

【 授权许可】

Unknown