# Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation

arXiv: https://arxiv.org/abs/2003.06555 · HTML: https://mlsanity.com/paper/2003.06555/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2020.

## Built on by (most cited first, 30 of 38)

- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks](https://mlsanity.com/paper/2302.02213/) (2023)
- [PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation](https://mlsanity.com/paper/2308.03979/) (2023)
- [Proximal Splitting Adversarial Attacks for Semantic Segmentation](https://mlsanity.com/paper/2206.07179/) (2022)
- [Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks](https://mlsanity.com/paper/2301.13487/) (2023)
- [Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks](https://mlsanity.com/paper/2302.02829/) (2023)
- [Adversarial Examples on Segmentation Models Can be Easy to Transfer](https://mlsanity.com/paper/2111.11368/) (2021)
- [UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation](https://mlsanity.com/paper/2410.09909/) (2024)
- [Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models](https://mlsanity.com/paper/2306.12941/) (2023)
- [Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion](https://mlsanity.com/paper/2402.09530/) (2024)
- [TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation](https://mlsanity.com/paper/2312.02207/) (2023)
- [Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation](https://mlsanity.com/paper/2310.17436/) (2023)
- [Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs](https://mlsanity.com/paper/2210.03429/) (2022)
- [Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs](https://mlsanity.com/paper/2208.12428/) (2022)
- [A Certified Radius-Guided Attack Framework to Image Segmentation Models](https://mlsanity.com/paper/2304.02693/) (2023)
- [Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation](https://mlsanity.com/paper/2305.12825/) (2023)
- [Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks](https://mlsanity.com/paper/2406.05857/) (2024)
- [Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training](https://mlsanity.com/paper/2411.02149/) (2024)
- [General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments](https://mlsanity.com/paper/2212.05387/) (2022)
- [Transferable Attack for Semantic Segmentation](https://mlsanity.com/paper/2307.16572/) (2023)
- [PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation](https://mlsanity.com/paper/2305.15709/) (2023)
- [Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness](https://mlsanity.com/paper/2601.14950/) (2026)
- [Safety Metrics for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2105.10142/) (2021)
- [Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation](https://mlsanity.com/paper/2208.06283/) (2022)
- [Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement](https://mlsanity.com/paper/2401.01750/) (2024)
- [Single-Step Adversarial Training for Semantic Segmentation](https://mlsanity.com/paper/2106.15998/) (2021)
- [On Evaluating the Adversarial Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/2306.14217/) (2023)
- [Exploring the Robustness of Human Parsers Towards Common Corruptions](https://mlsanity.com/paper/2309.00938/) (2023)
- [Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation](https://mlsanity.com/paper/2406.01425/) (2024)
- [Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off](https://mlsanity.com/paper/2407.09150/) (2024)

## Abstract (arXiv)

Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task. The effect of this type of training on semantic segmentation, contrarily, just commences. We make the initial attempt to explore the defense strategy on semantic segmentation by formulating a general adversarial training procedure that can perform decently on both adversarial and clean samples. We propose a dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect, by setting additional branches in the target model during training, and dealing with pixels with diverse properties towards adversarial perturbation. Our dynamical division mechanism divides pixels into multiple branches automatically. Note all these additional branches can be abandoned during inference and thus leave no extra parameter and computation cost. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets, in which DDC-AT yields satisfying performance under both white- and black-box attack.