mlsanityData to 7 Oct 2026

Robust Semantic Segmentation with Superpixel-Mix

arXiv 2108.00968 ↗First posted 2 Aug 2021cs.CV cs.AI stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce Superpixel-mix, a new superpixel-based data augmentation method with teacher-student consistency training. Unlike other mixing-based augmentation techniques, mixing superpixels between images is aware of object boundaries, while yielding consistent gains in segmentation accuracy. Our proposed technique achieves state-of-the-art results in semi-supervised semantic segmentation on the Cityscapes dataset. Moreover, Superpixel-mix improves the reliability of semantic segmentation by reducing network uncertainty and bias, as confirmed by competitive results under strong distributions shift (adverse weather, image corruptions) and when facing out-of-distribution data.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 68 of its 97 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

68 of 97 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  11. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  9. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  13. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  14. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  15. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  16. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  17. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  18. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  19. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  20. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  21. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  22. 2015A Neural Algorithm of Artistic Stylecited by 480
  23. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  24. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  25. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  26. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  27. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  28. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  29. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  30. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  31. 2017Dilated Residual Networkscited by 293
  32. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  33. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  34. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  35. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  36. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  37. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  38. 2020Training independent subnetworks for robust predictioncited by 177

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 5; 2024: 4; 2025: 2; 2026: 1.

19 papers.

Sort:

By area:

  1. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  2. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  3. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  4. 2022Latent Discriminant deterministic Uncertaintycited by 17
  5. 2024Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix Itcited by 11
  6. 2023Improving CLIP Robustness with Knowledge Distillation and Self-Trainingcited by 6
  7. 20232D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentationcited by 6
  8. 2024Benchmarking Segmentation Models with Mask-Preserved Attribute Editingcited by 6
  9. 2024The BRAVO Semantic Segmentation Challenge Results in UNCV2024cited by 6
  10. 2023Tailoring Mixup to Data for Calibrationcited by 5
  11. 2021ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignmentcited by 4
  12. 2022SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentationcited by 2
7 more
  1. 2023Learning to Generate Training Datasets for Robust Semantic Segmentationcited by 2
  2. 2023Rethinking Superpixel Segmentation from Biologically Inspired Mechanismscited by 2
  3. 2025D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognitioncited by 2
  4. 2026Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editingcited by 2
  5. 2022Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentationcited by 1
  6. 2024Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentationcited by 1
  7. 2025HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentationcited by 0