Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes...
Main Authors: | Tachetti, Andrea, Voinea, Stephen, Evangelopoulos, Georgios |
---|---|
Format: | Technical Report |
Language: | en_US |
Published: |
Center for Brains, Minds and Machines (CBMM), arXiv
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/107446 |
Similar Items
-
Learning An Invariant Speech Representation
by: Evangelopoulos, Georgios, et al.
Published: (2015) -
HUMAN EMOTION RECOGNITION SYSTEM USING DEEP LEARNING ALGORITHMS
by: Kateryna Yuvchenko, et al.
Published: (2022-09-01) -
Seedling Discrimination with Shape Features Derived from a Distance Transform
by: Rasmus Nyholm Jørgensen, et al.
Published: (2013-04-01) -
ViCTer: A semi-supervised video character tracker
by: Zilinghan Li, et al.
Published: (2023-06-01) -
Rectified Linear Units and Adaptive Moment Estimation Optimizer on ANN with Saved Model Prediction to Improve The Stock Price Prediction Framework Performance
by: Sekhudin Sekhudin, et al.
Published: (2023-08-01)