Quantum Probabilistic Label Refining: Enhancing Label Quality for Robust Image Classification

• URL: http://arxiv.org/abs/2510.00528v1
• Date: Wed, 01 Oct 2025 05:21:29 GMT
• Title: Quantum Probabilistic Label Refining: Enhancing Label Quality for Robust Image Classification
• Abstract summary: Learning with softmax cross-entropy on one-hot labels often leads to overconfident predictions and poor robustness under noise or perturbations.<n>We propose a hybrid quantum-classical framework that leverages quantum non-determinism to refine data labels into probabilistic ones.
• Score: 30.87772545335523
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Learning with softmax cross-entropy on one-hot labels often leads to overconfident predictions and poor robustness under noise or perturbations. Label smoothing mitigates this by redistributing some confidence uniformly, but treats all samples equally, ignoring intra-class variability. We propose a hybrid quantum-classical framework that leverages quantum non-determinism to refine data labels into probabilistic ones, offering more nuanced, human-like uncertainty representations than label smoothing or Bayesian approaches. A variational quantum circuit (VQC) encodes inputs into multi-qubit quantum states, using entanglement and superposition to capture subtle feature correlations. Measurement via the Born rule extracts probabilistic soft labels that reflect input-specific uncertainty. These labels are then used to train a classical convolutional neural network (CNN) with soft-target cross-entropy loss. On MNIST and Fashion-MNIST, our method improves robustness, achieving up to 50% higher accuracy under noise while maintaining competitive accuracy on clean data. It also enhances model calibration and interpretability, as CNN outputs better reflect quantum-derived uncertainty. This work introduces Quantum Probabilistic Label Refining, bridging quantum measurement and classical deep learning for robust training via refined, correlation-aware labels without architectural changes or adversarial techniques.

Related papers

• Discretization-Aware Fine-Tuning for Quantum Machine Learning with Chemical Foundation Models [0.0]
  Key challenge in practical quantum machine learning (QML) is the limited capacity of near-term quantum devices to encode high-dimensional classical data into small quantum registers.<n>We introduce discretization-aware fine-tuning (DAFT), a method that adapts a pre-trained chemical foundation model to produce representations that remain informative after quantization.<n>We evaluate both quantum and classical models under a controlled setting in which they receive identical discretized bit-string inputs.
  arXiv  Detail & Related papers  (2026-09-02T23:36:29Z)
• SLT: Robust Quantum Neural Networks for Noisy-Label Medical Image Classification via Supermartingale-based Label Transition [7.9871241094193435]
  Noisy-label learning in small-scale medical image classification is challenging and hinders the superiority of deep neural networks.<n>Recent studies suggest that quantum neural networks (QNNs) have shown potential in limited-data regimes.<n>We propose Supermartingale-based Label Transition (SLT), an anchor-free loss correction framework for robust QNN-based medical image classification under noisy labels.
  arXiv  Detail & Related papers  (2026-07-13T06:37:29Z)
• Q-BAR: Blogger Anomaly Recognition via Quantum-enhanced Manifold Learning [0.0]
  In recommendation-driven online media, creators increasingly suffer from semantic mutation, where malicious secondary edits preserve visual fidelity while altering the intended meaning.<n>We propose quantum-enhanced blogger anomaly recognition (Q-BAR), a hybrid quantum-classical framework to detect semantic anomalies in low-data regimes.<n>On a curated dataset of 100 creators, our quantum-enhanced approach achieves robust detection performance with significantly fewer trainable parameters compared to classical baselines.
  arXiv  Detail & Related papers  (2025-12-11T19:39:45Z)
• DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning [83.94574004953346]
  Semi-supervised multi-label learning aims to leverage unlabeled data to improve the model's performance.<n>Most existing methods assign equal weights to all pseudo-labels regardless of their quality.<n>We propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights.
  arXiv  Detail & Related papers  (2025-11-25T11:55:02Z)
• Semi-Supervised Regression with Heteroscedastic Pseudo-Labels [50.54050677867914]
  We propose an uncertainty-aware pseudo-labeling framework that dynamically adjusts pseudo-label influence from a bi-level optimization perspective.<n>We provide theoretical insights and extensive experiments to validate our approach across various benchmark SSR datasets.
  arXiv  Detail & Related papers  (2025-10-17T03:06:23Z)
• A Quantum Bagging Algorithm with Unsupervised Base Learners for Label Corrupted Datasets [2.850389822151216]
  We propose a quantum bagging framework that uses QMeans clustering as the base learner to reduce prediction variance and enhance robustness to label noise.<n>We demonstrate that the proposed quantum bagging algorithm performs comparably to its classical counterpart using KMeans while exhibiting greater resilience to label corruption than supervised bagging methods.
  arXiv  Detail & Related papers  (2025-09-08T09:34:33Z)
• Quantum Active Learning [3.3202982522589934]
  Training a quantum neural network typically demands a substantial labeled training set for supervised learning. QAL effectively trains the model, achieving performance comparable to that on fully labeled datasets. We elucidate the negative result of QAL being overtaken by random sampling baseline through miscellaneous numerical experiments.
  arXiv  Detail & Related papers  (2024-05-28T14:39:54Z)
• Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling [29.744621356187764]
  This paper presents SeqUST, a novel uncertain-aware self-training framework for Neural sequence labeling (NSL) We incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation at the token level and then select reliable language tokens from unlabeled data. A well-designed masked sequence labeling task with a noise-robust loss supports robust training, which aims to suppress the problem of noisy pseudo labels.
  arXiv  Detail & Related papers  (2023-02-17T02:40:04Z)
• SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning [101.86916775218403]
  This paper revisits the popular pseudo-labeling methods via a unified sample weighting formulation. We propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.
  arXiv  Detail & Related papers  (2023-01-26T03:53:25Z)
• CLS: Cross Labeling Supervision for Semi-Supervised Learning [9.929229055862491]
  Cross Labeling Supervision ( CLS) is a framework that generalizes the typical pseudo-labeling process. CLS allows the creation of both pseudo and complementary labels to support both positive and negative learning.
  arXiv  Detail & Related papers  (2022-02-17T08:09:40Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• 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)
• Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model [80.91927573604438]
  This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
  arXiv  Detail & Related papers  (2021-01-14T05:43:51Z)
• Quantum noise protects quantum classifiers against adversaries [120.08771960032033]
  Noise in quantum information processing is often viewed as a disruptive and difficult-to-avoid feature, especially in near-term quantum technologies. We show that by taking advantage of depolarisation noise in quantum circuits for classification, a robustness bound against adversaries can be derived. This is the first quantum protocol that can be used against the most general adversaries.
  arXiv  Detail & Related papers  (2020-03-20T17:56:14Z)

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.