Object identification from few examples by improving the invariance of a Deep Convolutional Neural Network

By Giulia Pasquale, Carlo Ciliberto, Lorenzo Rosasco, Lorenzo Natale. 2016

59 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

CORe50: a New Dataset and Benchmark for Continuous Object Recognition (2017, methodology): “Finally, the iCubWorld datasets ([22], [23]) have been acquired in a robotic vision context and are the closest ones to CORe50.”
Continual Learning for Robotics (2019, methodology): “, 2015; Lomonaco and Maltoni, 2016) iCubWorldTransformation X (Pasquale et al., 2016; Camoriano et al., 2017) LSUN X (Wu et al.”
Exploring the Challenges towards Lifelong Fact Learning (2018, background): “focus proposed the iCUBWorld-Transf dataset [21] with 200 real objects divided in 20 categories.”
New Metrics and Experimental Paradigms for Continual Learning (2018, background): “Two of the largest datasets for continual learning experiments are iCubWorld Transformations (iCub-T) [11] and CORe50 [10].”
Stream-51: Streaming Classification and Novelty Detection from Videos (2020, background): “0 (iCub-1) [12] and iCub World Transformations (iCub-T) [33].”
Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting (2018, methodology): “RGB-D [25] - 51 300 T BIG BIRD [26] - - 100 T ICUB 28 [20] 4 7 28 H ICUB World [21] 6 20 200 H Core50 [17] 11 10 50 H IVOS 12 12 36 H”
Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition (2019, methodology): “Most of previous work in the robot vision literature used statistical learning tools, dealing with continuous learning of known classes for semantic spatial models [11] or incremental class learning of object models [12], [13].”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, background): “4) Robotics: In recent years, there has been a growing interest in using deep learning architectures in advanced robotics [87], [88].”
Online Continual Learning on Sequences (2020, methodology): “OpenLORIS [66] 19 69 7 500 RGB-D moving cam.”
Progress in Neuroengineering for brain repair: New challenges and open issues (2018, background): “A similar problem is being studied in robotics for training visual recognition systems from small dataset (Pasquale et al., 2016; Schwarz et al., 2015).”