.png){kind=icon}
返回
A sparse focus framework for visual fine-grained classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-021-10872-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The location of discriminative features and reduction of model complexity are the two main research directions in fine-grained image classification. The manual annotation of object is very labor-intensive, and the commonly used model compression methods usually reduce the classification accuracy while compressing the model. In this paper, we propose a Sparse Focus Framework(SFF) based on Bilinear Convolutional Neural Network(BCNN), which includes self-focus module and sparse scaling factors. The focus module like the focus function of human beings automatically locates the object from background without manual labeling, and only a small amount of computing resources are occupied in the guaranteed accuracy. The sparse scaling factor for each channel can evaluate the importance of feature channels, which is adopted in pruning of channels. The large number of parameters and calculations in the fine-grained classification model can been effectively reduced by pruning method adopted in our network, which can obtain a sparse structure to prevent overfitting while maintaining classification performance. Our experimental results show that our model obtains accuracy of 90.2%, 84.5% and 92.0% on FGVC-aircraft, Stanford dogs and Stanford cars, respectively. Compared with the highest classification accuracy obtained by the same classification network B-CNN[D,D], the accuracy gains with 6.1%, 4.1% and 1.4% respectively. Moreover, the channel-level sparsity effectively reduces 30% of the network parameters and nearly 13% of the computation.
Keyword:
Fine-grained visual recognition
Sparse focus framework
Network sparsity
Network pruning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
暂无机构信息
引用论文
The effect of a novel extracorporeal cytokine hemoadsorption device on IL-6 elimination in septic patients: A randomized controlled trial.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Dropout vs. batch normalization: an empirical study of their impact to deep learning辍学与批量归一化: 对深度学习影响的实证研究
PREAI
分享收藏Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression propertiesRSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容