mlsanityData to 7 Oct 2026

Confidence Estimation Using Unlabeled Data

arXiv 2307.10440 ↗First posted 19 Jul 2023cs.LG cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this paper, we propose the first confidence estimation method for a semi-supervised setting, when most training labels are unavailable. We stipulate that even with limited training labels, we can still reasonably approximate the confidence of model on unlabeled samples by inspecting the prediction consistency through the training process. We use training consistency as a surrogate function and propose a consistency ranking loss for confidence estimation. On both image classification and segmentation tasks, our method achieves state-of-the-art performances in confidence estimation. Furthermore, we show the benefit of the proposed method through a downstream active learning task. The code is available at https://github.com/TopoXLab/consistency-ranking-loss

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

30 of 45 references.

References · 30

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  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. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  11. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
18 more
  1. 2017Selective Classification for Deep Neural Networkscited by 799
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  3. 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
  4. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  5. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  6. 2019Learning Loss for Active Learningcited by 335
  7. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  8. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  9. 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
  10. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  11. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  12. 2018Bias-Reduced Uncertainty Estimation for Deep Neural Classifierscited by 106
  13. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 95
  14. 2019Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentationcited by 75
  15. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  16. 2017Distance-based Confidence Score for Neural Network Classifierscited by 30
  17. 2021Deep Probability Estimationcited by 14
  18. 2021Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehiclescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 1.

8 papers.

  1. 2023Calibrating Uncertainty for Semi-Supervised Crowd Countingcited by 22
  2. 2025MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentationcited by 6
  3. 2024Spatial Diffusion for Cell Layout Generationcited by 5
  4. 2025MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentationcited by 3
  5. 2026ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Modelscited by 3
  6. 2025Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariancecited by 1
  7. 2024Learning Topological Representations for Deep Image Understandingcited by 0
  8. 2025Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDAcited by 0