Task-Driven Feature Pooling for Image Classification

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Task-Driven Feature Pooling for Image Classification
	Xie, Guo-Sen; Zhang, Xu-Yao; Shu Xiangbo; Yan Shuicheng; Cheng-Lin Liu
	2015
会议名称	IEEE International Conference on Computer Vision
会议录名称	ICCV
会议日期	2015-12
会议地点	智利，圣地亚哥
摘要	Feature pooling is an important strategy to achieve high performance in image classification. However, most pooling methods are unsupervised and heuristic. In this paper, we propose a novel task-driven pooling (TDP) model to directly learn the pooled representation from data in a discriminative manner. Different from the traditional methods (e.g., average and max pooling), TDP is an implicit pooling method which elegantly integrates the learning of representations into the given classification task. The optimization of TDP can equalize the similarities between the descriptors and the learned representation, and maximize the classification accuracy. TDP can be combined with the traditional BoW models (coding vectors) or the recent stateof-the-art CNN models (feature maps) to achieve a much better pooled representation. Furthermore, a self-training mechanism is used to generate the TDP representation for a new test image. A multi-task extension of TDP is also proposed to further improve the performance. Experiments on three databases (Flower-17, Indoor-67 and Caltech-101) well validate the effectiveness of our models.
关键词	Pooling Cnn
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11956
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Xie, Guo-Sen
推荐引用方式 GB/T 7714	Xie, Guo-Sen,Zhang, Xu-Yao,Shu Xiangbo,et al. Task-Driven Feature Pooling for Image Classification[C],2015.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Xie_ICCV_2015_paper.（1263KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载