# Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation

arXiv: https://arxiv.org/abs/2004.11072 · HTML: https://mlsanity.com/paper/2004.11072/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2020.

## Built on by (most cited first, 26 of 26)

- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras](https://mlsanity.com/paper/2104.04420/) (2021)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [Detecting Adversarial Perturbations in Multi-Task Perception](https://mlsanity.com/paper/2203.01177/) (2022)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation](https://mlsanity.com/paper/2310.17436/) (2023)
- [UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks](https://mlsanity.com/paper/2108.04584/) (2021)
- [Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation](https://mlsanity.com/paper/2305.12825/) (2023)
- [GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks](https://mlsanity.com/paper/2302.02907/) (2023)
- [Improving Online Performance Prediction for Semantic Segmentation](https://mlsanity.com/paper/2104.05255/) (2021)
- [Safety Metrics for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2105.10142/) (2021)
- [Sensitivity analysis of AI-based algorithms for autonomous driving on optical wavefront aberrations induced by the windshield](https://mlsanity.com/paper/2308.11711/) (2023)
- [Examining Common Paradigms in Multi-Task Learning](https://mlsanity.com/paper/2311.04698/) (2023)
- [Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task](https://mlsanity.com/paper/2105.13531/) (2021)
- [On Evaluating the Adversarial Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/2306.14217/) (2023)
- [Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off](https://mlsanity.com/paper/2407.09150/) (2024)
- [Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis](https://mlsanity.com/paper/2408.10021/) (2024)
- [Integrating uncertainty quantification into randomized smoothing based robustness guarantees](https://mlsanity.com/paper/2410.20432/) (2024)
- [Boosting Supervised Learning Performance with Co-training](https://mlsanity.com/paper/2111.09797/) (2021)
- [Work In Progress: Safety and Robustness Verification of Autoencoder-Based Regression Models using the NNV Tool](https://mlsanity.com/paper/2207.06759/) (2022)
- [Evaluating and Enhancing Segmentation Model Robustness with Metamorphic Testing](https://mlsanity.com/paper/2504.02335/) (2025)
- [Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation](https://mlsanity.com/paper/2606.09536/) (2026)
- [Multi-Task Consistency-based Detection of Adversarial Attacks](https://mlsanity.com/paper/2608.07750/) (2026)
- [Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks](https://mlsanity.com/paper/2608.11815/) (2026)

## Abstract (arXiv)

While current approaches for neural network training often aim at improving performance, less focus is put on training methods aiming at robustness towards varying noise conditions or directed attacks by adversarial examples. In this paper, we propose to improve robustness by a multi-task training, which extends supervised semantic segmentation by a self-supervised monocular depth estimation on unlabeled videos. This additional task is only performed during training to improve the semantic segmentation model's robustness at test time under several input perturbations. Moreover, we even find that our joint training approach also improves the performance of the model on the original (supervised) semantic segmentation task. Our evaluation exhibits a particular novelty in that it allows to mutually compare the effect of input noises and adversarial attacks on the robustness of the semantic segmentation. We show the effectiveness of our method on the Cityscapes dataset, where our multi-task training approach consistently outperforms the single-task semantic segmentation baseline in terms of both robustness vs. noise and in terms of adversarial attacks, without the need for depth labels in training.