# MSSSeg: Learning Multi-Scale Structural Complexity for Self-Supervised Segmentation

arXiv: https://arxiv.org/abs/2512.23997 · HTML: https://mlsanity.com/paper/2512.23997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018)
- [A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology](https://mlsanity.com/paper/1910.01877/) (2019)
- [Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2104.13613/) (2021)
- [Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2012.10782/) (2020)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2210.05944/) (2022)
- [Leveraging Hidden Positives for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2303.15014/) (2023)
- [TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2112.01515/) (2021)
- [EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2403.01482/) (2024)
- [Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation](https://mlsanity.com/paper/2203.11160/) (2022)
- [Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling](https://mlsanity.com/paper/2309.12378/) (2023)
- [Causal Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2310.07379/) (2023)
- [Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals](https://mlsanity.com/paper/2404.16818/) (2024)
- [Self-supervised Semantic Segmentation Grounded in Visual Concepts](https://mlsanity.com/paper/2203.13868/) (2022)

## Abstract (arXiv)

Self-supervised semantic segmentation methods often suffer from structural errors, including merging distinct objects or fragmenting coherent regions, because they rely primarily on low-level appearance cues such as color and texture. These cues lack structural discriminability: they carry no information about the structural organization of a region, making it difficult to distinguish boundaries between similar-looking objects or maintain coherence within internally varying regions. Recent approaches attempt to address this by incorporating depth priors, yet remain limited by not explicitly modeling structural complexity that persists even when appearance cues are ambiguous. To bridge this gap, we present MSSSeg, a framework that explicitly learns multi-scale structural complexity from both semantic and depth domains, via three coupled components: (1) a Differentiable Box-Counting (DBC) module that captures and aligns multi-scale structural complexity features with semantic features; (2) a Learnable Structural Augmentation (StructAug) that corrupts pixel-intensity patterns, forcing the network to rely on structural complexity features from DBC; and (3) a Persistent Homology Loss (PHLoss) that directly supervises the structural complexity of predicted segmentations. Extensive experiments demonstrate that MSSSeg achieves new state-of-the-art performance on COCO-Stuff-27, Cityscapes, and Potsdam without excessive computational overhead, validating that explicit structural complexity learning is crucial for self-supervised segmentation.