mlsanityData to 7 Oct 2026

CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Loss

arXiv 2504.17813 ↗First posted 22 Apr 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In ordinal classification, misclassifying neighboring ranks is common, yet the consequences of these errors are not the same. For example, misclassifying benign tumor categories is less consequential, compared to an error at the pre-cancerous to cancerous threshold, which could profoundly influence treatment choices. Despite this, existing ordinal classification methods do not account for the varying importance of these margins, treating all neighboring classes as equally significant. To address this limitation, we propose CLOC, a new margin-based contrastive learning method for ordinal classification that learns an ordered representation based on the optimization of multiple margins with a novel multi-margin n-pair loss (MMNP). CLOC enables flexible decision boundaries across key adjacent categories, facilitating smooth transitions between classes and reducing the risk of overfitting to biases present in the training data. We provide empirical discussion regarding the properties of MMNP and show experimental results on five real-world image datasets (Adience, Historical Colour Image Dating, Knee Osteoarthritis, Indian Diabetic Retinopathy Image, and Breast Carcinoma Subtyping) and one synthetic dataset simulating clinical decision bias. Our results demonstrate that CLOC outperforms existing ordinal classification methods and show the interpretability and controllability of CLOC in learning meaningful, ordered representations that align with clinical and practical needs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 66 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

24 of 66 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2020Supervised Contrastive Learningcited by 2,803
  7. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  8. 2020Understanding the Behaviour of Contrastive Losscited by 397
  9. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  10. 2021BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Imagescited by 130
  11. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  12. 2022Rank-N-Contrast: Learning Continuous Representations for Regressioncited by 74
12 more
  1. 2021Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regressioncited by 58
  2. 2022RankSim: Ranking Similarity Regularization for Deep Imbalanced Regressioncited by 52
  3. 2021Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classificationcited by 49
  4. 2022Moving Window Regression: A Novel Approach to Ordinal Regressioncited by 44
  5. 2022OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regressioncited by 44
  6. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  7. 2020Driver Anomaly Detection: A Dataset and Contrastive Learning Approachcited by 41
  8. 2021Max-Margin Contrastive Learningcited by 27
  9. 2023Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classificationcited by 21
  10. 2024Teach CLIP to Develop a Number Sense for Ordinal Regressioncited by 20
  11. 2016Apparent Age Estimation Using Ensemble of Deep Learning Modelscited by 4
  12. 2023Understanding Contrastive Learning Through the Lens of Marginscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2026T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalabilitycited by 2
  2. 2025An Effective Strategy for Modeling Score Ordinality and Non-uniform Intervals in Automated Speaking Assessmentcited by 0
  3. 2025Learning To Defer To A Population With Limited Demonstrationscited by 0
  4. 2025Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecastingcited by 0
  5. 2026Understanding Annotation Error Propagation and Learning an Adaptive Policy for Expert Intervention in Barrett's Video Segmentationcited by 0
  6. 2026Directed Ordinal Diffusion Regularization for Progression-Aware Diabetic Retinopathy Gradingcited by 0
  7. 2026Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Datacited by 0
  8. 2026Contrastive Order Learning: A General Framework for Ordinal Regressioncited by 0
  9. 2026D3O: Dynamic Distribution Distillation for Ordinal Regressioncited by 0
  10. 2026DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Featurescited by 0
  11. 20263rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimationcited by 0