# Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning

arXiv: https://arxiv.org/abs/2303.00396 · HTML: https://mlsanity.com/paper/2303.00396/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 49 references that are in the map.
- First posted on arXiv 1 Mar 2023.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Metric Learning with Adaptive Density Discrimination](https://mlsanity.com/paper/1511.05939/) (2015)
- [Unimodal probability distributions for deep ordinal classification](https://mlsanity.com/paper/1705.05278/) (2017)
- [An Image is Worth More than a Thousand Favorites: Surfacing the Hidden Beauty of Flickr Pictures](https://mlsanity.com/paper/1505.03358/) (2015)
- [Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities](https://mlsanity.com/paper/2011.07607/) (2020)

## Built on by (most cited first, 2 of 2)

- [Ordinal Multiple-instance Learning for Ulcerative Colitis Severity Estimation with Selective Aggregated Transformer](https://mlsanity.com/paper/2411.14750/) (2024)
- [Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer](https://mlsanity.com/paper/2504.20530/) (2025)

## Abstract (arXiv)

For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout in feature space would be that the sample clusters are arranged in class order along a straight line in space. However, enforcing samples to conform to a specific layout in the feature space is a challenging problem. To address this problem, in this paper, we propose a novel Constrained Proxies Learning (CPL) method, which can learn a proxy for each ordinal class and then adjusts the global layout of classes by constraining these proxies. Specifically, we propose two kinds of strategies: hard layout constraint and soft layout constraint. The hard layout constraint is realized by directly controlling the generation of proxies to force them to be placed in a strict linear layout or semicircular layout (i.e., two instantiations of strict ordinal layout). The soft layout constraint is realized by constraining that the proxy layout should always produce unimodal proxy-to-proxies similarity distribution for each proxy (i.e., to be a relaxed ordinal layout). Experiments show that the proposed CPL method outperforms previous deep ordinal classification methods under the same setting of feature extractor.