Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

ICIP2017_Incremental zero-shot learning based on attributes for image classification

Abstract: 

Instead of assuming a closed-world environment comprising a fixed number of objects, modern pattern recognition systems need to recognize outliers, identify anomalies, or discover entirely new objects, which is known as zero-shot object recognition. However, many existing zero-shot learning methods are not efficient enough to incrementally update themselves with new samples mixed with known or novel class labels. In this paper, we propose an incremental zero-shot learning framework (IIAP/QR) based on indirect-attribute-prediction (IAP) model. Firstly, a fast incremental
classifier based on null space based linear discriminant analysis with QR-updating (NLDA/QR) is put forward, which can solve small-sample-size (SSS) problem and unequal-samplesize (USS) problem that usually occur in incremental learning using the centroid of each class as input. Then with the probabilistic inference of Class-Attribute layer and Attribute-Zero shot classification layer, IIAP/QR model can efficiently update itself for the insertion of both new samples to the existing class and totally novel classes with comparable recognition accuracy for zero-shot object recognition.

up
0 users have voted:

Paper Details

Authors:
Nan Xue, Yi Wang, Xin Fan, Maomao Min
Submitted On:
15 September 2017 - 3:07am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Nan Xue
Document Year:
2017
Cite

Document Files

ICIP2017 conference slide of paper 1688

(23)

Subscribe

[1] Nan Xue, Yi Wang, Xin Fan, Maomao Min, "ICIP2017_Incremental zero-shot learning based on attributes for image classification", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2087. Accessed: Jul. 20, 2019.
@article{2087-17,
url = {http://sigport.org/2087},
author = {Nan Xue; Yi Wang; Xin Fan; Maomao Min },
publisher = {IEEE SigPort},
title = {ICIP2017_Incremental zero-shot learning based on attributes for image classification},
year = {2017} }
TY - EJOUR
T1 - ICIP2017_Incremental zero-shot learning based on attributes for image classification
AU - Nan Xue; Yi Wang; Xin Fan; Maomao Min
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2087
ER -
Nan Xue, Yi Wang, Xin Fan, Maomao Min. (2017). ICIP2017_Incremental zero-shot learning based on attributes for image classification. IEEE SigPort. http://sigport.org/2087
Nan Xue, Yi Wang, Xin Fan, Maomao Min, 2017. ICIP2017_Incremental zero-shot learning based on attributes for image classification. Available at: http://sigport.org/2087.
Nan Xue, Yi Wang, Xin Fan, Maomao Min. (2017). "ICIP2017_Incremental zero-shot learning based on attributes for image classification." Web.
1. Nan Xue, Yi Wang, Xin Fan, Maomao Min. ICIP2017_Incremental zero-shot learning based on attributes for image classification [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2087