Data to 14 Oct 2026

Benchmarking the Robustness of Semantic Segmentation Models

arXiv 1908.05005 ↗First posted 14 Aug 2019cs.CV eess.IVcited by 111

Not on the map. Why?

Abstract (arXiv)

When designing a semantic segmentation module for a practical application, such as autonomous driving, it is crucial to understand the robustness of the module with respect to a wide range of image corruptions. While there are recent robustness studies for full-image classification, we are the first to present an exhaustive study for semantic segmentation, based on the state-of-the-art model DeepLabv3+. To increase the realism of our study, we utilize almost 400,000 images generated from Cityscapes, PASCAL VOC 2012, and ADE20K. Based on the benchmark study, we gain several new insights. Firstly, contrary to full-image classification, model robustness increases with model performance, in most cases. Secondly, some architecture properties affect robustness significantly, such as a Dense Prediction Cell, which was designed to maximize performance on clean data only.

Key facts. Cited by 111 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 17; 2023: 29; 2024: 16; 2025: 16; 2026: 17.

111 papers.

Sort:

By area:

2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
2022Vision Transformer Adapter for Dense Predictionscited by 565
2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
2022Understanding The Robustness in Vision Transformerscited by 144
2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 129
20223D Common Corruptions and Data Augmentationcited by 119
2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 68
2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 54
2022Towards Robust Referring Image Segmentationcited by 49
2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 49

38 more

2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
2021Improving robustness against common corruptions with frequency biased modelscited by 34
2021Benchmarking the Robustness of Spatial-Temporal Models Against Corruptionscited by 34
2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 32
2022Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditionscited by 31
2023Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Modelscited by 31
2023Robustness of SAM: Segment Anything Under Corruptions and Beyondcited by 31
2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
2023Semantic Image Segmentation: Two Decades of Researchcited by 27
2022Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathologycited by 26
2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
2023An Empirical Study on the Robustness of the Segment Anything Model (SAM)cited by 23
2023Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-Endcited by 23
2022Does Robustness on ImageNet Transfer to Downstream Tasks?cited by 20
2023Benchmarking the Robustness of LiDAR Semantic Segmentation Modelscited by 18
2024Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classificationcited by 18
2022Latent Discriminant deterministic Uncertaintycited by 17
2023EDAPS: Enhanced Domain-Adaptive Panoptic Segmentationcited by 17
2023Reliability in Semantic Segmentation: Are We on the Right Track?cited by 16
2021Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attackcited by 15
2023Temporal Coherent Test-Time Optimization for Robust Video Classificationcited by 15
2023MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentationcited by 14
2023Robustness Analysis on Foundational Segmentation Modelscited by 13
2023Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformerscited by 13
2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 13
2023IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weathercited by 12
2024Visual Robustness Benchmark for Visual Question Answering (VQA)cited by 12
2022Towards Robust Video Object Segmentation with Adaptive Object Calibrationcited by 11
2024Trapped in texture bias? A large scale comparison of deep instance segmentationcited by 10
2024An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domainscited by 10
2021Benchmarks for Corruption Invariant Person Re-identificationcited by 9
2021Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shiftcited by 8
2021Benchmarking the Robustness of Instance Segmentation Modelscited by 8
2023U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentationcited by 8
2021Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shiftscited by 7
2022Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrationscited by 7
2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7

50 most cited of 111 All 111 (JSON)