IMAGE CLASSIFICATION USING RBM TO ENCODE LOCAL DESCRIPTORS WITH GROUP SPARSE LEARNING | |
Wang, Jinzhu ; Wang, Wenmin ; Wang, Ronggang ; Gao, Wen | |
2015 | |
关键词 | Image Classification Feature Coding Restricted Boltzmann Machine (RBM) Group Sparse Learning (GSL) FEATURES SCALE |
英文摘要 | This paper proposes to employ deep learningmodel to encode local descriptors for image classification. Previous works using deep architectures to obtain higher representations are often operated from pixel level, which lack the power to be generalized to large-size and complex images due to computational burdens and internal essence capture. Our method slips the leash of this limitation by starting from local descriptors to leverage more semantical inputs. We investigate to use two layers of Restricted Boltzmann Machines (RBMs) to encode different local descriptors with a novel group sparse learning (GSL) inspired by the recent success of sparse coding. Besides, unlike the most existing pure unsupervised feature coding strategies, we use another RBM corresponding to semantic labels to perform supervised fine-tuning which makes our model more suitable for classification task. Experimental results on Caltech-256 and Indoor-67 datasets demonstrate the effectiveness of our method.; CPCI-S(ISTP); wangjz@sz.pku.edu.cn; wangwm@ece.pku.edu.cn; rgwang@pkusz.edu.cn; wgao@pku.edu.cn; 912-916 |
语种 | 英语 |
出处 | 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/446336] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Wang, Jinzhu,Wang, Wenmin,Wang, Ronggang,et al. IMAGE CLASSIFICATION USING RBM TO ENCODE LOCAL DESCRIPTORS WITH GROUP SPARSE LEARNING. 2015-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论