Back to Search
Start Over
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
- Source :
- Scientific Reports, Scientific Reports, 2016, 6, pp.32672. ⟨10.1038/srep32672⟩, Scientific Reports, Nature Publishing Group, 2016, 6, pp.32672. ⟨10.1038/srep32672⟩
- Publication Year :
- 2015
-
Abstract
- Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
- Subjects :
- [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Variation (game tree)
Convolutional neural network
Article
050105 experimental psychology
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
03 medical and health sciences
0302 clinical medicine
Humans
0501 psychology and cognitive sciences
Vision, Ocular
Backward masking
Multidisciplinary
Hierarchy (mathematics)
business.industry
05 social sciences
Cognitive neuroscience of visual object recognition
Feed forward
Pattern recognition
Object (computer science)
Receptive field
FOS: Biological sciences
Quantitative Biology - Neurons and Cognition
Human visual system model
Visual Perception
Neurons and Cognition (q-bio.NC)
Artificial intelligence
Nerve Net
business
030217 neurology & neurosurgery
Subjects
Details
- Language :
- English
- ISSN :
- 20452322
- Database :
- OpenAIRE
- Journal :
- Scientific Reports, Scientific Reports, 2016, 6, pp.32672. ⟨10.1038/srep32672⟩, Scientific Reports, Nature Publishing Group, 2016, 6, pp.32672. ⟨10.1038/srep32672⟩
- Accession number :
- edsair.doi.dedup.....2ef957f10d64e32902657768d50d317b