mlsanityData to 14 Oct 2026

Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation

arXiv 2411.15763 ↗First posted 24 Nov 2024cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Deep learning has seen remarkable advancements in machine learning, yet it often demands extensive annotated data. Tasks like 3D semantic segmentation impose a substantial annotation burden, especially in domains like medicine, where expert annotations drive up the cost. Active learning (AL) holds great potential to alleviate this annotation burden in 3D medical segmentation. The majority of existing AL methods, however, are not tailored to the medical domain. While weakly-supervised methods have been explored to reduce annotation burden, the fusion of AL with weak supervision remains unexplored, despite its potential to significantly reduce annotation costs. Additionally, there is little focus on slice-based AL for 3D segmentation, which can also significantly reduce costs in comparison to conventional volume-based AL. This paper introduces a novel metric learning method for Coreset to perform slice-based active learning in 3D medical segmentation. By merging contrastive learning with inherent data groupings in medical imaging, we learn a metric that emphasizes the relevant differences in samples for training 3D medical segmentation models. We perform comprehensive evaluations using both weak and full annotations across four datasets (medical and non-medical). Our findings demonstrate that our approach surpasses existing active learning techniques on both weak and full annotations and obtains superior performance with low-annotation budgets which is crucial in medical imaging. Source code for this project is available in the supplementary materials and on GitHub: https://github.com/arvindmvepa/al-seg.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 57 of its 92 references that are in the map. First posted on arXiv 24 Nov 2024.

Builds on

57 of 92 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  7. 2020Supervised Contrastive Learningcited by 2,829
  8. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  9. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  10. 2017Deep Bayesian Active Learning with Image Datacited by 819
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  12. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
38 more
  1. 2019Variational Adversarial Active Learningcited by 284
  2. 2017No Fuss Distance Metric Learning using Proxiescited by 226
  3. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  4. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  5. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  6. 20203D Self-Supervised Methods for Medical Imagingcited by 134
  7. 2016Multivariate mixture model for myocardium segmentation combining multi-source imagescited by 133
  8. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  9. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  10. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  11. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  12. 2020Annotation-efficient deep learning for automatic medical image segmentationcited by 79
  13. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  14. 2022CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervisioncited by 64
  15. 2022Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervisioncited by 64
  16. 2023LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matchingcited by 60
  17. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 54
  18. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  19. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  20. 2021Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentationcited by 45
  21. 2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
  22. 2023BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizabilitycited by 42
  23. 2019MIC: Mining Interclass Characteristics for Improved Metric Learningcited by 41
  24. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  25. 2018Deep Metric Learning with BIER: Boosting Independent Embeddings Robustlycited by 40
  26. 2019Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentationcited by 32
  27. 2019Interactive segmentation of medical images through fully convolutional neural networkscited by 29
  28. 2022Transformer based multiple instance learning for weakly supervised histopathology image segmentationcited by 26
  29. 2023Active learning for medical image segmentation with stochastic batchescited by 21
  30. 2018Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensemblescited by 20
  31. 2021Boosting Active Learning via Improving Test Performancecited by 19
  32. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  33. 2021Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregationcited by 18
  34. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  35. 2018Deep Randomized Ensembles for Metric Learningcited by 17
  36. 2022Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotationscited by 15
  37. 2018Large-Scale Visual Active Learning with Deep Probabilistic Ensemblescited by 13
  38. 2023Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational modelcited by 13

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localizationcited by 7
  2. 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentationcited by 3
  3. 2025Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selectioncited by 1
  4. 2026Finally Outshining the Random Baseline: A Simple and Effective Solution for Active Learning in 3D Biomedical Imagingcited by 1
  5. 2026Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learningcited by 1
  6. 2026EAGT: Echocardiography Augmentation for Generalisability and Transferabilitycited by 1
  7. 2026Group-invariant Coresets for Data-efficient Active Learningcited by 0
  8. 2026UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localizationcited by 0