Elliott, Andrew;
Russell, Chris;
Law, Wai Pan Stephen;
(2020)
Object Localisation using Perturbations on the Perceptual Bal.
In:
Proceedings of the 2020 ICML Workshop on Human Interpretability in Machine Learning (WHI 2020).
ICML
Preview |
Text
object_localisation_using_perturbations.pdf - Accepted Version Download (5MB) | Preview |
Abstract
We present a simple regularisation of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are semi-sparse alterations that highlight objects and regions of interest while leaving the background unaltered. We demonstrate the merits of our approach by evaluating on a standard explainability benchmark for object localisation. As a semantically meaningful adverse perturbations, it forms a bridge between counterfactual explanations and adversarial perturbations in the space of images.
| Type: | Proceedings paper |
|---|---|
| Title: | Object Localisation using Perturbations on the Perceptual Bal |
| Event: | 5th ICML Workshop on Human Interpretability in Machine Learning (WHI) |
| Location: | virtual |
| Dates: | 17 Jul 2020 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://sites.google.com/view/whi2020/ |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS > Dept of Geography |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10183513 |
Archive Staff Only
 |
View Item |
