# Learning Invariant Inter-pixel Correlations for Superpixel Generation

arXiv: https://arxiv.org/abs/2402.18201 · HTML: https://mlsanity.com/paper/2402.18201/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation](https://mlsanity.com/paper/1812.09912/) (2018)
- [Superpixel Convolutional Networks using Bilateral Inceptions](https://mlsanity.com/paper/1511.06739/) (2015)
- [AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation](https://mlsanity.com/paper/2101.10696/) (2021)
- [gSLICr: SLIC superpixels at over 250Hz](https://mlsanity.com/paper/1509.04232/) (2015)

## Built on by (most cited first, 5 of 5)

- [Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation](https://mlsanity.com/paper/2509.12791/) (2025)
- [Superpixel Segmentation: A Long-Lasting Ill-Posed Problem](https://mlsanity.com/paper/2411.06478/) (2024)
- [Bridging Granularity Gaps: Hierarchical Semantic Learning for Cross-domain Few-shot Segmentation](https://mlsanity.com/paper/2511.12200/) (2025)
- [H-SPAM: Hierarchical Superpixel Anything Model](https://mlsanity.com/paper/2604.11218/) (2026)
- [Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation](https://mlsanity.com/paper/2606.24296/) (2026)

## Abstract (arXiv)

Deep superpixel algorithms have made remarkable strides by substituting hand-crafted features with learnable ones. Nevertheless, we observe that existing deep superpixel methods, serving as mid-level representation operations, remain sensitive to the statistical properties (e.g., color distribution, high-level semantics) embedded within the training dataset. Consequently, learnable features exhibit constrained discriminative capability, resulting in unsatisfactory pixel grouping performance, particularly in untrainable application scenarios. To address this issue, we propose the Content Disentangle Superpixel (CDS) algorithm to selectively separate the invariant inter-pixel correlations and statistical properties, i.e., style noise. Specifically, We first construct auxiliary modalities that are homologous to the original RGB image but have substantial stylistic variations. Then, driven by mutual information, we propose the local-grid correlation alignment across modalities to reduce the distribution discrepancy of adaptively selected features and learn invariant inter-pixel correlations. Afterwards, we perform global-style mutual information minimization to enforce the separation of invariant content and train data styles. The experimental results on four benchmark datasets demonstrate the superiority of our approach to existing state-of-the-art methods, regarding boundary adherence, generalization, and efficiency. Code and pre-trained model are available at https://github.com/rookiie/CDSpixel.