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

arXiv: https://arxiv.org/abs/2504.17813 · HTML: https://mlsanity.com/paper/2504.17813/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 66 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification](https://mlsanity.com/paper/2106.08808/) (2021)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression](https://mlsanity.com/paper/2206.02338/) (2022)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Driver Anomaly Detection: A Dataset and Contrastive Learning Approach](https://mlsanity.com/paper/2009.14660/) (2020)
- [Max-Margin Contrastive Learning](https://mlsanity.com/paper/2112.11450/) (2021)
- [Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification](https://mlsanity.com/paper/2306.13856/) (2023)
- [Teach CLIP to Develop a Number Sense for Ordinal Regression](https://mlsanity.com/paper/2408.03574/) (2024)
- [Apparent Age Estimation Using Ensemble of Deep Learning Models](https://mlsanity.com/paper/1606.02909/) (2016)
- [Understanding Contrastive Learning Through the Lens of Margins](https://mlsanity.com/paper/2306.11526/) (2023)

## Built on by (most cited first, 11 of 11)

- [T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability](https://mlsanity.com/paper/2604.18573/) (2026)
- [An Effective Strategy for Modeling Score Ordinality and Non-uniform Intervals in Automated Speaking Assessment](https://mlsanity.com/paper/2509.03372/) (2025)
- [Learning To Defer To A Population With Limited Demonstrations](https://mlsanity.com/paper/2510.19351/) (2025)
- [Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2511.10200/) (2025)
- [Understanding Annotation Error Propagation and Learning an Adaptive Policy for Expert Intervention in Barrett's Video Segmentation](https://mlsanity.com/paper/2602.21855/) (2026)
- [Directed Ordinal Diffusion Regularization for Progression-Aware Diabetic Retinopathy Grading](https://mlsanity.com/paper/2602.21942/) (2026)
- [Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data](https://mlsanity.com/paper/2607.08103/) (2026)
- [Contrastive Order Learning: A General Framework for Ordinal Regression](https://mlsanity.com/paper/2607.08109/) (2026)
- [D3O: Dynamic Distribution Distillation for Ordinal Regression](https://mlsanity.com/paper/2607.23575/) (2026)
- [DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features](https://mlsanity.com/paper/2608.04652/) (2026)
- [3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation](https://mlsanity.com/paper/2609.10187/) (2026)

## 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.