Mining web images for concept learning
Author
Golge, Eren
Advisor
Duygulu, Pınar
Date
2014-08Publisher
Bilkent University
Language
English
Type
ThesisItem Usage Stats
80
views
views
30
downloads
downloads
Abstract
We attack the problem of learning concepts automatically from noisy Web image
search results. The idea is based on discovering common characteristics shared among
category images by posing two novel methods that are able to organise the data while
eliminating irrelevant instances. We propose a novel clustering and outlier detection
method, namely Concept Map (CMAP). Given an image collection returned for a concept
query, CMAP provides clusters pruned from outliers. Each cluster is used to train
a model representing a different characteristics of the concept. One another method is
Association through Model Evolution (AME). It prunes the data in an iterative manner
and it progressively finds better set of images with an evaluational score computed
for each iteration. The idea is based on capturing discriminativeness and representativeness
of each instance against large number of random images and eliminating the
outliers. The final model is used for classification of novel images. These two methods
are applied on different benchmark problems and we observed compelling or better
results compared to state of art methods.
Keywords
Weakly-supervised learningConcept learning
Rectifying self-organizing map
Association with model evolution
Clustering and outlier detection
Conceptmap
Attributes
Object recognition
Scene classification
Face identification
Feature learning
Permalink
http://hdl.handle.net/11693/14002Collections
The following license files are associated with this item: