Humans and deep networks largely agree on which kinds of variation make object recognition harder.
Saeed Reza KheradpishehMasoud GhodratiMohammad GanjtabeshTimothée MasquelierPublished in: CoRR (2016)
Keyphrases
- object recognition
- computer vision
- machine vision systems
- social networks
- natural images
- unsupervised learning
- image representation
- network structure
- network analysis
- high level
- data sets
- heterogeneous networks
- scene classification
- complex networks
- np complete
- image understanding
- human behavior
- human experts
- feature detection
- object class
- small world
- constrained search
- object detection