Incremental zero-shot learning based on attributes for image classification
Lists
Only you see this
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-sample-size (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.
BibTeX
@inproceedings{xue2017incremental,
author = {Nan Xue and Yi Wang and Xin Fan and Maomao Min},
title = {{Incremental zero-shot learning based on attributes for image classification}},
booktitle = {ICIP},
year = {2017},
url = {https://openreview.net/forum?id=I9WTQIOEXu},
}Loading related content...