CASIA OpenIR  > 模式识别实验室
DF2Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification.
Li Yabei1,2; Zhang Junge1,2; Cheng Yanhua3; Huang Kaiqi1,2,4; Tan Tieniu1,2,4
Conference NameThe Thirty-Second AAAI Conference on Artificial Intelligence (AAAI)
Conference Date2018.2.2-2.8
Conference PlaceNew Orleans, USA
Contribution Rank1

This paper focuses on the task of RGB-D indoor scene classification. It is a very challenging task due to two folds. 1)
Learning robust representation for indoor scene is difficult
because of various objects and layouts. 2) Fusing the complementary cues in RGB and Depth is nontrivial since there
are large semantic gaps between the two modalities. Most existing works learn representation for classification by training
a deep network with softmax loss and fuse the two modalities by simply concatenating the features of them. However,
these pipelines do not explicitly consider intra-class and interclass similarity as well as inter-modal intrinsic relationships.
To address these problems, this paper proposes a Discriminative Feature Learning and Fusion Network (DF2Net) with
two-stage training. In the first stage, to better represent scene
in each modality, a deep multi-task network is constructed to
simultaneously minimize the structured loss and the softmax
loss. In the second stage, we design a novel discriminative
fusion network which is able to learn correlative features of
multiple modalities and distinctive features of each modality.
Extensive analysis and experiments on SUN RGB-D Dataset
and NYU Depth Dataset V2 show the superiority of DF2Net
over other state-of-the-art methods in RGB-D indoor scene
classification task.

Indexed ByEI
Document Type会议论文
2.University of Chinese Academy of Sciences
3.Tencent Wechat AI
4.CAS Center for Excellence in Brain Science and Intelligence Technology
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li Yabei,Zhang Junge,Cheng Yanhua,et al. DF2Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification.[C],2018.
Files in This Item:
File Name/Size DocType Version Access License
Li-Zhang.pdf(24122KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li Yabei]'s Articles
[Zhang Junge]'s Articles
[Cheng Yanhua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li Yabei]'s Articles
[Zhang Junge]'s Articles
[Cheng Yanhua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li Yabei]'s Articles
[Zhang Junge]'s Articles
[Cheng Yanhua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Li-Zhang.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.