Research map / Detection and segmentation / CNN features
Benchmarking the Robustness of Semantic Segmentation Models
Christoph Kamann, Carsten Rother
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a higher-performing Xception backbone | DeepLabv3+ · Cityscapes validation, clean and most corruption types | mIoU | Improved |
| Add atrous convolutions to the backbone (ablation) | DeepLabv3+ Xception-71 · Cityscapes validation, Gaussian noise | mIoU: 7.7 -> 14.9 | Improved |
| Keep ASPP rather than removing it (ablation) | DeepLabv3+ Xception-71 · Cityscapes validation, clean | mIoU: 73.9 -> 78.6 | Improved |
| Use ASPP rather than replacing it with DPC (ablation) | DeepLabv3+ Xception-71 · Cityscapes validation, Gaussian noise | mIoU: 7.3 -> 14.9 | Improved |
| Add global average pooling (ablation) | DeepLabv3+ Xception-71 · Cityscapes validation, Gaussian noise | mIoU: 14.9 -> 9.7 | Hurt |
| Remove the long-range link (ablation) | DeepLabv3+ Xception-71 · Cityscapes validation, Gaussian noise | mIoU: 14.9 -> 13.9 | Hurt |
Closest papers by meaning
- Benchmarking the Robustness of Semantic Segmentation Models with Respect to Common Corruptions (IJCV 2020 · similarity 0.95)
- Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers (ECCV 2020 · similarity 0.91)
- Reliability in Semantic Segmentation: Are We on the Right Track? (CVPR 2023 · similarity 0.91)
- Benchmarking the Robustness of LiDAR Semantic Segmentation Models (IJCV 2024 · similarity 0.90)
- Benchmarking Segmentation Models with Mask-Preserved Attribute Editing (CVPR 2024 · similarity 0.86)
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
