mlsanityData to 7 Oct 2026

Transparency Distortion Robustness for SOTA Image Segmentation Tasks

arXiv 2405.12864 ↗First posted 21 May 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Semantic Image Segmentation facilitates a multitude of real-world applications ranging from autonomous driving over industrial process supervision to vision aids for human beings. These models are usually trained in a supervised fashion using example inputs. Distribution Shifts between these examples and the inputs in operation may cause erroneous segmentations. The robustness of semantic segmentation models against distribution shifts caused by differing camera or lighting setups, lens distortions, adversarial inputs and image corruptions has been topic of recent research. However, robustness against spatially varying radial distortion effects that can be caused by uneven glass structures (e.g. windows) or the chaotic refraction in heated air has not been addressed by the research community yet. We propose a method to synthetically augment existing datasets with spatially varying distortions. Our experiments show, that these distortion effects degrade the performance of state-of-the-art segmentation models. Pretraining and enlarged model capacities proof to be suitable strategies for mitigating performance degradation to some degree, while fine-tuning on distorted images only leads to marginal performance improvements.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 21 May 2024.

Builds on

43 of 55 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2023Segment Anythingcited by 8,158
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2013Intriguing properties of neural networkscited by 5,114
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
31 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  4. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  5. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  6. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  10. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  11. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  12. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  13. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  14. 2018Generalisation in humans and deep neural networkscited by 237
  15. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  16. 2021Partial success in closing the gap between human and machine visioncited by 185
  17. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  18. 2018Pyramid Attention Network for Semantic Segmentationcited by 148
  19. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 137
  20. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  21. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  22. 2020Segmenting Transparent Objects in the Wildcited by 98
  23. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  24. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  25. 2018Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Camerascited by 42
  26. 2023Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentationcited by 37
  27. 2019A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D imagescited by 29
  28. 2018TernausNetV2: Fully Convolutional Network for Instance Segmentationcited by 25
  29. 2020Universal Semantic Segmentation for Fisheye Urban Driving Imagescited by 25
  30. 2019Semantic Segmentation of Panoramic Images Using a Synthetic Datasetcited by 15
  31. 2017Quality Resilient Deep Neural Networkscited by 12

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learningcited by 0
  2. 2025Evaluating and Enhancing Segmentation Model Robustness with Metamorphic Testingcited by 0