Object Recognition, Localization and Grasp Detection Using a Unified Deep Convolutional Neural Network with Multi-task Loss

2018 ◽  
Author(s):  
Qun Jia ◽  
Zhiqiang Cao ◽  
Xionglei Zhao ◽  
Lei Pang ◽  
Yingying Yu ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Recognition ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network

scholarly journals The number sense is an emergent property of a deep convolutional neural network trained for object recognition

2019 ◽  
Author(s):  
Nicholas K. DeWind
Keyword(s):  
Neural Network ◽  
Visual Cortex ◽  
Object Recognition ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Number Sense ◽  
Emergent Property ◽  
Deep Convolutional Neural Network ◽  
Mathematical Concepts ◽  
Representational Space

SummaryHumans and many non-human animals have the “number sense,” an ability to estimate the number of items in a set without counting. This innate sense of number is hypothesized to provide a foundation for more complex numerical and mathematical concepts. Here I investigated whether we also share the number sense with a deep convolutional neural network (DCNN) trained for object recognition. These in silico networks have revolutionized machine learning over the last seven years, allowing computers to reach human-level performance on object recognition tasks for the first time. Their architecture is based on the structure of mammalian visual cortex, and after they are trained, they provide a highly predictive model of responses in primate visual cortex, suggesting deep homologies. I found that the DCNN demonstrates three key hallmarks of the number sense: numerosity-selective units (analogous to biological neurons), the behavioral ratio effect, and ordinality over representational space. Because the DCNN was not trained to enumerate, I conclude that the number sense is an emergent property of the network, the result of some combination of the network architecture and the constraint to develop the complex representational structure necessary for object recognition. By analogy I conclude that the number sense in animals was not necessarily the result of direct selective pressure to enumerate but might have “come for free” with the evolution of a complex visual system that evolved to identify objects and scenes in the real world.

scholarly journals A Deep Convolutional Neural Network to Detect the Existence of Geospatial Elements in High-Resolution Aerial Imagery

Proceedings ◽  
2019 ◽  
Vol 19 (1) ◽  
pp. 17 ◽  
Author(s):  
Calimanut-Ionut Cira ◽  
Ramón Alcarria ◽  
Miguel-Ángel Manso-Callejo ◽  
Francisco Serradilla
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Road Network ◽  
Deep Convolutional Neural Network ◽  
Aerial Imagery ◽  
Learning Techniques

This paper tackles the problem of object recognition in high-resolution aerial imagery and addresses the application of Deep Learning techniques to solve a challenge related to detecting the existence of geospatial elements (road network) in the available cartographic support. This challenge is addressed by building a convolutional neural network (CNN) trained to detect roads in high resolution aerial orthophotos divided in tiles (256 × 256 pixels) using manually labelled data.

LENS CLASSIFICATION ACCORDING TO THE TYPE OF LIGHT SPOT USING A NEURAL NETWORK

2020 ◽  
Vol 2020 (4) ◽  
pp. 4-14
Author(s):  
Vladimir Budak ◽  
Ekaterina Ilyina
Keyword(s):  
Neural Network ◽  
Light Intensity ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Beam Angle ◽  
New Model ◽  
Technical Parameters ◽  
Transfer Training ◽  
Trained Network

The article proposes the classification of lenses with different symmetrical beam angles and offers a scale as a spot-light’s palette. A collection of spotlight’s images was created and classified according to the proposed scale. The analysis of 788 pcs of existing lenses and reflectors with different LEDs and COBs carried out, and the dependence of the axial light intensity from beam angle was obtained. A transfer training of new deep convolutional neural network (CNN) based on the pre-trained GoogleNet was performed using this collection. GradCAM analysis showed that the trained network correctly identifies the features of objects. This work allows us to classify arbitrary spotlights with an accuracy of about 80 %. Thus, light designer can determine the class of spotlight and corresponding type of lens with its technical parameters using this new model based on CCN.

Sign in / Sign up

Export Citation Format

Share Document