When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2509.16704v1
• Date: Sat, 20 Sep 2025 14:23:09 GMT
• Title: When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation
• Authors: Pan Liu, Jinshi Liu,
• Abstract summary: We present Confidence Separable Learning (CSL) as a convex optimization problem within the confidence distribution feature space.<n>CSL formulates pseudo-label selection as a convex optimization problem within the confidence distribution feature space.<n>We show that CSL performs favorably against state-of-the-art methods.
• Score: 15.149171763610662
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence predictions as pseudo-labels. However, these methods cannot cope with network overconfidence tendency, where correct and incorrect predictions overlap significantly in high-confidence regions, making separation challenging and amplifying model cognitive bias. Meanwhile, the direct discarding of low-confidence predictions disrupts spatial-semantic continuity, causing critical context loss. We propose Confidence Separable Learning (CSL) to address these limitations. CSL formulates pseudo-label selection as a convex optimization problem within the confidence distribution feature space, establishing sample-specific decision boundaries to distinguish reliable from unreliable predictions. Additionally, CSL introduces random masking of reliable pixels to guide the network in learning contextual relationships from low-reliability regions, thereby mitigating the adverse effects of discarding uncertain predictions. Extensive experimental results on the Pascal, Cityscapes, and COCO benchmarks show that CSL performs favorably against state-of-the-art methods. Code and model weights are available at https://github.com/PanLiuCSU/CSL.

Related papers

• Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning [58.331709210563616]
  Thinking by Subtraction is a confidence-driven contrastive decoding approach.<n>A small subset of low-confidence tokens disproportionately contributes to reasoning errors and unnecessary output expansion.<n>Our method, Confidence-Driven Contrastive Decoding, detects low-confidence tokens during decoding and intervenes at these positions.
  arXiv  Detail & Related papers  (2026-02-20T14:13:22Z)
• A Confidence-Variance Theory for Pseudo-Label Selection in Semi-Supervised Learning [15.149171763610662]
  This paper introduces a Confidence-Variance (CoVar) theory framework that provides a principled joint reliability criterion for pseudo-label selection.<n>We show that reliable pseudo-labels should have both high MC and low RCV, and that the influence of RCV increases as confidence grows.<n>We integrate CoVar as a plug-in module into representative semi-supervised semantic segmentation and image classification methods.
  arXiv  Detail & Related papers  (2026-01-16T02:51:59Z)
• Perceive, Act and Correct: Confidence Is Not Enough for Hyperspectral Classification [22.167975466562822]
  Confidence alone is often misleading in hyperspectral image classification, as models tend to mistake high predictive scores for correctness while lacking awareness of uncertainty.<n>We propose CABIN, a semi-supervised framework that addresses this limitation through a closed-loop learning process of perception, action, and correction.
  arXiv  Detail & Related papers  (2025-11-13T08:14:32Z)
• MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentation [26.75334172633309]
  Semi-Supervised Learning is important for reducing the annotation cost for medical image segmentation models.<n>We propose a universal framework MetaSSL based on a spatially heterogeneous loss.<n>Our method is plug-and-play and general to most existing SSL methods.
  arXiv  Detail & Related papers  (2025-09-01T05:45:08Z)
• CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation [26.585985828583304]
  Semi-supervised semantic segmentation (SSSS) aims to improve performance by utilizing large amounts of unlabeled data with limited labeled samples.<n>Existing methods often suffer from coupling, where over-reliance on initial labeled data leads to suboptimal learning.<n>We propose CW-BASS, a novel framework for SSSS that mitigates the impact of incorrect predictions and boundary blur.
  arXiv  Detail & Related papers  (2025-02-21T02:24:10Z)
• Do not trust what you trust: Miscalibration in Semi-supervised Learning [21.20806568508201]
  State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. We show that SSL methods based on pseudo-labels are significantly miscalibrated, and formally demonstrate the minimization of the min-entropy. We integrate a simple penalty term, which enforces the logit of the predictions on unlabeled samples to remain low, preventing the network predictions to become overconfident.
  arXiv  Detail & Related papers  (2024-03-22T18:43:46Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Leveraging Unlabeled Data for 3D Medical Image Segmentation through Self-Supervised Contrastive Learning [3.7395287262521717]
  Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information. We introduce two distinctworks designed to explore and exploit the discrepancies between them, ultimately correcting the erroneous prediction results. We employ a self-supervised contrastive learning paradigm to distinguish between reliable and unreliable predictions.
  arXiv  Detail & Related papers  (2023-11-21T14:03:16Z)
• Exploiting Low-confidence Pseudo-labels for Source-free Object Detection [54.98300313452037]
  Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation phase. We propose a new approach to take full advantage of pseudo-labels by introducing high and low confidence thresholds.
  arXiv  Detail & Related papers  (2023-10-19T12:59:55Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• Contrastive Credibility Propagation for Reliable Semi-Supervised Learning [6.014538614447467]
  We propose Contrastive Credibility Propagation (CCP) for deep SSL via iterative transductive pseudo-label refinement. CCP unifies semi-supervised learning and noisy label learning for the goal of reliably outperforming a supervised baseline in any data scenario.
  arXiv  Detail & Related papers  (2022-11-17T23:01:47Z)
• Confident Sinkhorn Allocation for Pseudo-Labeling [40.883130133661304]
  Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. This paper studies theoretically the role of uncertainty to pseudo-labeling and proposes Confident Sinkhorn Allocation (CSA) CSA identifies the best pseudo-label allocation via optimal transport to only samples with high confidence scores.
  arXiv  Detail & Related papers  (2022-06-13T02:16:26Z)
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning [53.1047775185362]
  Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models. We propose an uncertainty-aware pseudo-label selection (UPS) framework which improves pseudo labeling accuracy by drastically reducing the amount of noise encountered in the training process.
  arXiv  Detail & Related papers  (2021-01-15T23:29:57Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.