# Robust Image Ordinal Regression with Controllable Image Generation

arXiv: https://arxiv.org/abs/2305.04213 · HTML: https://mlsanity.com/paper/2305.04213/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 7 May 2023.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [Horizon Lines in the Wild](https://mlsanity.com/paper/1604.02129/) (2016)
- [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)
- [Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field](https://mlsanity.com/paper/2107.06360/) (2021)
- [Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels](https://mlsanity.com/paper/1805.11837/) (2018)

## Built on by (most cited first, 8 of 8)

- [Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning](https://mlsanity.com/paper/2402.02334/) (2024)
- [A Survey on Ordinal Regression: Applications, Advances and Prospects](https://mlsanity.com/paper/2503.00952/) (2025)
- [OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM](https://mlsanity.com/paper/2504.04801/) (2025)
- [Uncertainty-Aware Multi-Expert Knowledge Distillation for Imbalanced Disease Grading](https://mlsanity.com/paper/2505.00592/) (2025)
- [Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression](https://mlsanity.com/paper/2505.05834/) (2025)
- [Provably Minimum-Length Conformal Prediction Sets for Ordinal Classification](https://mlsanity.com/paper/2511.16845/) (2025)
- [Ranking-aware Reinforcement Learning for Ordinal Ranking](https://mlsanity.com/paper/2601.20585/) (2026)
- [Ordinal Diffusion Models for Color Fundus Images](https://mlsanity.com/paper/2602.24013/) (2026)

## Abstract (arXiv)

Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framework called CIG based on controllable image generation to directly tackle these two issues. Our main idea is to generate extra training samples with specific labels near category boundaries, and the sample generation is biased toward the less-represented categories. To achieve controllable image generation, we seek to separate structural and categorical information of images based on structural similarity, categorical similarity, and reconstruction constraints. We evaluate the effectiveness of our new CIG approach in three different image ordinal regression scenarios. The results demonstrate that CIG can be flexibly integrated with off-the-shelf image encoders or ordinal regression models to achieve improvement, and further, the improvement is more significant for minority categories.