mlsanityData to 7 Oct 2026

Bayesian Active Learning for Semantic Segmentation

arXiv 2408.01694 ↗First posted 3 Aug 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Fully supervised training of semantic segmentation models is costly and challenging because each pixel within an image needs to be labeled. Therefore, the sparse pixel-level annotation methods have been introduced to train models with a subset of pixels within each image. We introduce a Bayesian active learning framework based on sparse pixel-level annotation that utilizes a pixel-level Bayesian uncertainty measure based on Balanced Entropy (BalEnt) [84]. BalEnt captures the information between the models' predicted marginalized probability distribution and the pixel labels. BalEnt has linear scalability with a closed analytical form and can be calculated independently per pixel without relational computations with other pixels. We train our proposed active learning framework for Cityscapes, Camvid, ADE20K and VOC2012 benchmark datasets and show that it reaches supervised levels of mIoU using only a fraction of labeled pixels while outperforming the previous state-of-the-art active learning models with a large margin.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 76 of its 97 references that are in the map. First posted on arXiv 3 Aug 2024.

Builds on

76 of 97 references.

References · 76

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023Segment Anythingcited by 8,158
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
38 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  2. 2017Deep Bayesian Active Learning with Image Datacited by 812
  3. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  4. 2021Extract Free Dense Labels from CLIPcited by 580
  5. 2015Deep Kernel Learningcited by 440
  6. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  7. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  8. 2019Learning Loss for Active Learningcited by 335
  9. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  10. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  11. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  12. 2019Variational Adversarial Active Learningcited by 284
  13. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  14. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  15. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  16. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  17. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  18. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  19. 2022ReCo: Region-Controlled Text-to-Image Generationcited by 177
  20. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  21. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  22. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  23. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  24. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  25. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  26. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
  27. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 97
  28. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 95
  29. 2023CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationcited by 94
  30. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  31. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  32. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  33. 2017Extreme clicking for efficient object annotationcited by 80
  34. 2013SEEDS: Superpixels Extracted via Energy-Driven Samplingcited by 75
  35. 2024Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactivelycited by 74
  36. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
  37. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  38. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentationcited by 6
  2. 2025A2LC: Active and Automated Label Correction for Semantic Segmentationcited by 2
  3. 2025IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detectioncited by 2
  4. 2025Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentationcited by 0
  5. 2026iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervisioncited by 0