On the Robustness of Redundant Teacher-Student Frameworks for Semantic Segmentation

Andreas Bär, Fabian Hüger, Peter Schlicht, Tim Fingscheidt

Introduction

Deep Neural Networks (DNNs) have become the standard for semantic segmentation tasks, such as labeling pixels in autonomous driving scenes. However, these models are highly susceptible to adversarial examples (AEs)—carefully crafted inputs with imperceptible perturbations that lead to incorrect, high-confidence predictions. In safety-critical domains like autonomous driving, a static perception system can be "blinded" if an attacker gains knowledge of its architecture and weights. This paper investigates a redundant framework designed to enhance robustness by creating a "moving target" defense.

Methodology: The Redundant T-S-A Framework

The authors propose a Redundant Teacher-Student-Adaptive (T-S-A) framework consisting of three distinct models:

  1. Static Teacher ($\mathfrak{F}_T$): A high-capacity, pre-trained model.
  2. Static Student ($\mathfrak{F}_S$): A more efficient model trained to replicate the teacher's performance.
  3. Adaptive Student ($\mathfrak{F}_A$): A model initialized from the static student that undergoes continuous online adaptation using unlabeled data.
The Redundant T-S-A framework architecture.

The primary innovation is the Inverse Feature Matching (IFM) loss. While standard knowledge distillation encourages students to mimic teacher features, the IFM loss penalizes the adaptive student if its internal representations are too similar to those of the vulnerable static student. This forces the adaptive student to find alternative feature paths to the correct output, effectively moving it out of the "vulnerability subspace" targeted by static attacks.

Experimental Evaluation

The framework was evaluated using the Cityscapes dataset, utilizing 2,950 finely-annotated images for initial training and 19,998 coarsely-annotated images (with labels removed) for online adaptation. Robustness was measured using the mean Intersection over Union (mIoU) ratio, comparing performance on adversarial images versus clean images.

Key Results

The inclusion of IFM loss significantly improved the resilience of the adaptive student against adversarial attacks. As shown in the results table below, without the IFM defense, the adaptive student's performance dropped to 35.14% of its clean-image accuracy under a moderate attack (S-AE, $\epsilon=1$). With the IFM defense enabled, the model maintained 80.51% of its original accuracy.

Robustness results with and without IFM.

Discussion and Conclusion

The study demonstrates that intentional divergence from a known vulnerable model, guided by a high-performance teacher, is a viable defensive strategy. By constantly adapting on a stream of unlabeled data, the system presents a "moving target" that renders static adversarial maps obsolete.

While effective, this approach introduces a robustness-accuracy trade-off; the adaptive student's clean-image performance (approx. 53% mIoU) is lower than the static teacher's (approx. 75% mIoU). Future work will explore more sophisticated fusion strategies, such as majority voting among the three models, to further improve both base accuracy and overall system reliability in hostile environments.

Summary updated

Abstract

The trend towards autonomous systems in today's technology comes with the need for environment perception. Deep neural networks (DNNs) constantly showed state-of-the-art performance over the last few years in visual machine perception, e.g., semantic segmentation. While DNNs work fine on uncorrupted data, recently introduced adversarial examples (AEs) led to misclassification with high confidence. This lack of robustness against such adversarial attacks questions the use of DNNs in safety-critical autonomous systems, e.g., autonomous driving vehicles. In this work, we address the mentioned problem with the use of a redundant teacher-student framework, consisting of a static teacher network (T), a static student network (S), and a constantly adapting student network (A). By using this triplet in combination with a novel inverse feature matching (IFM) loss, we show that a significant robustness increase of student DNNs against adversarial attacks is achieveable, while maintaining semantic segmentation quality at a reasonably high level. With our approach, we manage to increase the mean intersection over union (mean IoU) ratio between static student adversarial examples and clean images from about 35 % to about 80 % on the Cityscapes dataset. Moreover, our proposed method can be integrated into any DNN-based perception mechanism to increase the (online) robustness in an adversarial environment, created from static model knowledge.
BibTeX
@inproceedings{bar2019robustness,
  author = {Andreas Bär and Fabian Hüger and Peter Schlicht and Tim Fingscheidt},
  title = {{On the Robustness of Redundant Teacher-Student Frameworks for Semantic Segmentation}},
  booktitle = {Workshops @ CVPR},
  year = {2019},
  doi = {10.1109/cvprw.2019.00178},
}
Figure