mlsanityData to 7 Oct 2026

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

arXiv 2112.05975 ↗First posted 11 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve semantics-biased selection. The subset is highlighted by vote entropy and then attended by Gaussian kernels to maximize the biased regions. We also propose a Contextual Labels Extension (CLE) to boost regional annotations with contextual attention guidance. With the collaboration of semantics-agnostic panoptic matching and regionbiased selection and extension, our CPRAL can strike a balance between labeling efforts and performance and compromise the semantics distribution. We perform extensive experiments on Cityscapes and BDD10K datasets and show that CPRAL outperforms the cutting-edge methods with impressive results and less labeling proportion.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 11 Dec 2021.

Builds on

37 of 58 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  10. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  11. 2019Learning Loss for Active Learningcited by 335
  12. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
25 more
  1. 2017Dilated Residual Networkscited by 293
  2. 2019Variational Adversarial Active Learningcited by 284
  3. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  4. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  5. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 100
  6. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 95
  7. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  8. 2021Multiple instance active learning for object detectioncited by 77
  9. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  10. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  11. 2019Active Learning for Deep Detection Neural Networkscited by 62
  12. 2020State-Relabeling Adversarial Active Learningcited by 60
  13. 2020Reinforced active learning for image segmentationcited by 56
  14. 2018Adversarial Sampling for Active Learningcited by 51
  15. 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 47
  16. 2017Cost-Effective Active Learning for Melanoma Segmentationcited by 40
  17. 2019Active Learning for Graph Neural Networks via Node Feature Propagationcited by 37
  18. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  19. 2018Cost-Sensitive Active Learning for Intracranial Hemorrhage Detectioncited by 28
  20. 2020VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learningcited by 25
  21. 2020MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Mapscited by 23
  22. 2020Suggestive Annotation of Brain Tumour Images with Gradient-guided Samplingcited by 19
  23. 2021Smart Scribbles for Image Matingcited by 11
  24. 2018Active Learning for Segmentation by Optimizing Content Information for Maximal Entropycited by 10
  25. 2021Multi-scale Information Assembly for Image Mattingcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 1.

6 papers.

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  2. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  3. 2023Adaptive Superpixel for Active Learning in Semantic Segmentationcited by 14
  4. 2022Large-Field Contextual Feature Learning for Glass Detectioncited by 8
  5. 2023SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learningcited by 8
  6. 2023Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessmentcited by 0