.png){kind=icon}
.png){kind=icon}
Return
Deep feature representation based on privileged knowledge transfer
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2017.12.004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Feature representation has been an elusive concept until neural networks become popular and exhibit the strong learning capability. However, as supervised labels provide a little meaningful information for feature representation, neural networks suffer from inadequate ability to acquire their representing knowledge by extracting patterns from raw data. To address this issue, in this paper, we propose a novel feature learning model by transferring the spatial relation information to the weights of neural networks. More specially, privileged knowledge stemmed from segmented image is fully utilized in distilling stage to perceive notable objects. The segmented image is regarded as a probability distribution of objects, the notable objects are fetched by maximizing lower bound of mutual information, instead of considering each image as an example of one-hot label. Through this way, spatial relation information is contributed to the feature learning besides class labels. This strategy, denoted as PKT-network, is applied to the image network training. Experimental results show that PKT-network performs excellently for multi-objects representation on Pascal VOC 2012 SegmentationClass (20 object classes) dataset and Microsoft COCO (80 object classes) dataset. (C) 2017 Elsevier B.V. All rights reserved.
Keywords:
Feature representation
Privileged knowledge transfer
Deep neural network
Multi-object retrieval
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W