What a difference a pixel makes: An empirical examination of features used by CNNs for categorisation

By Gaurav Malhotra, Jeffrey S. Bowers. 2018

3 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Matthias Bethge
2. Luc Van Gool
3. Wieland Brendel
4. Trevor Darrell
5. Richard S. Zemel
6. Bernt Schiele
7. Ming-Hsuan Yang
8. Dacheng Tao

In Model Architectures

1. Matthias Bethge
2. Richard S. Zemel
3. Felix Wichmann
4. Robert Geirhos
5. Wieland Brendel
6. Claudio Michaelis
7. Jörn-Henrik Jacobsen

Citations in the corpus

• Shortcut learning in deep neural networks (2020, background): “ (e.g. class-predictive pixels or image quality) and record the accuracy drop on clean test data as a way of finding out how prone a given architecture and loss function are to picking up on shortcuts [39,40,100,41]. is a test where the majority of current models struggle. Typically, the space of all”