Robustness Evaluation and Adversarial Training of an Instance Segmentation Model

06/02/2022
by   Jacob Bond, et al.
0

To evaluate the robustness of non-classifier models, we propose probabilistic local equivalence, based on the notion of randomized smoothing, as a way to quantitatively evaluate the robustness of an arbitrary function. In addition, to understand the effect of adversarial training on non-classifiers and to investigate the level of robustness that can be obtained without degrading performance on the training distribution, we apply Fast is Better than Free adversarial training together with the TRADES robust loss to the training of an instance segmentation network. In this direction, we were able to achieve a symmetric best dice score of 0.85 on the TuSimple lane detection challenge, outperforming the standardly-trained network's score of 0.82. Additionally, we were able to obtain an F-measure of 0.49 on manipulated inputs, in contrast to the standardly-trained network's score of 0. We show that probabilisitic local equivalence is able to successfully distinguish between standardly-trained and adversarially-trained models, providing another view of the improved robustness of the adversarially-trained models.

READ FULL TEXT

page 3

page 5

page 6

research
10/13/2020

To be Robust or to be Fair: Towards Fairness in Adversarial Training

Adversarial training algorithms have been proven to be reliable to impro...
research
10/05/2020

Geometry-aware Instance-reweighted Adversarial Training

In adversarial machine learning, there was a common belief that robustne...
research
04/17/2018

Robust Machine Comprehension Models via Adversarial Training

It is shown that many published models for the Stanford Question Answeri...
research
06/30/2021

Local Reweighting for Adversarial Training

Instances-reweighted adversarial training (IRAT) can significantly boost...
research
09/10/2019

Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification

Today's state-of-the-art image classifiers fail to correctly classify ca...
research
05/19/2020

Enhancing Certified Robustness of Smoothed Classifiers via Weighted Model Ensembling

Randomized smoothing has achieved state-of-the-art certified robustness ...
research
12/21/2020

Adversarial training for continuous robustness control problem in power systems

We propose a new adversarial training approach for injecting robustness ...

Please sign up or login with your details

Forgot password? Click here to reset