Paper Info
Title
Unsupervised Generation of Context-Relevant Training-Sets for Visual Object Recognition Employing Multilinguality
Abstract
Image based object classification requires clean training data sets. Gathering such sets is usually done manually by humans, which is time-consuming and laborious. On the other hand, directly using images from search engines creates very noisy data due to ambiguous noun-focused indexing. However, in daily speech nouns and verbs are always coupled. We use this for the automatic generation of clean data sets by the here-presented TRANSCLEAN algorithm, which „ through the use of multiple languages „ also solves the problem of polyesters (a single spelling with multiple meanings). Thus, we use the implicit knowledge contained in verbs, e.g. in an imperative such as \"hit the nail\", implicating a metal nail and not the fingernail. One type of reference application where this method can automatically operate is human-robot collaboration based on discourse. A second is the generation of clean image data sets, where tedious manual cleaning can be replaced by the much simpler manual generation of a single relevant verb-noun topple. Here we show the impact of our improved training sets for several widely used and state-of-the-art classifiers including Multipath Hierarchical Matching Pursuit. All tested classifiers show a substantial boost of about +20% in recognition performance.
Year
DOI
Venue
2015
10.1109/WACV.2015.112
Applications of Computer Vision
Keywords
Field
DocType
image classification,indexing,iterative methods,natural language processing,object recognition,unsupervised learning,transclean algorithm,automatic clean data set generation,clean image data sets,fingernail,hit the nail,human-robot collaboration,image based object classification,metal nail,multilinguality,multipath hierarchical matching pursuit,noun-focused indexing,polysemes,search engines,unsupervised context-relevant training-set generation,verb-noun tuple,visual object recognition,clutter
Multipath propagation,Matching pursuit,Computer vision,Data set,Pattern recognition,Computer science,Clutter,Noun,Search engine indexing,Spelling,Artificial intelligence,Cognitive neuroscience of visual object recognition
Conference
ISSN
Citations 
PageRank 
2472-6737
0
0.34
References 
Authors
22
4
Name
Order
Citations
PageRank
Markus Schoeler11455.98
Florentin Wörgötter21304119.30
Tomas Kulvicius313514.05
Jeremie Papon419910.18