Golge, E., & Duygulu, P.. ConceptMap:Mining noisy web data for concept learning , The European Conference on Computer Vision (ECCV) 2014.
We attack the problem of learning concepts automatically from noisy
Web image search results. The idea is based on discovering common characteristics shared among subsets of images by posing a method that is 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. The proposed method outperforms the state-of-the-art studies on the
task of learning from noisy web data for low-level attributes, as well as high level
object categories. It is also competitive with the supervised methods in learning
scene concepts. Moreover, results on naming faces support the generalisation capability of the CMAP framework to different domains. CMAP is capable to work
at large scale with no supervision through exploiting the available sources
CMAP in runtime. It shows the unit updates from iteration 1 to saturation where the units are precisely defined.
Visual Examples --
ConceptMap attribute clusters and outliers.
ConceptMap face results.
Tasks and Datasets --
We give compelling experimental results for the different tasks;