On the Scale Invariance in State of the Art CNNs Trained on ImageNet
The diffused practice of pre-training Convolutional Neural Networks (CNNs) on large natural image datasets such as ImageNet causes the automatic learning of invariance to object scale variations. This, however, can be detrimental in medical imaging, where pixel spacing has a known physical correspon...
Main Authors: | Mara Graziani, Thomas Lompech, Henning Müller, Adrien Depeursinge, Vincent Andrearczyk |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Machine Learning and Knowledge Extraction |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-4990/3/2/19 |
Similar Items
-
Invariant theory /
by: Neusel, Mara D., 1964-
Published: (2007) -
Is it enough to optimize CNN architectures on ImageNet?
by: Lukas Tuggener, et al.
Published: (2022-11-01) -
Scaling Metric Measurement Invariance Models
by: Eric Klopp, et al.
Published: (2023-09-01) -
Invariant theory /
by: 316273 Fogarty, John
Published: (1969) -
ImageNet Large Scale Visual Recognition Challenge
by: Russakovsky, Olga, et al.
Published: (2016)