# Unsupervised Class Generation to Expand Semantic Segmentation Datasets

arXiv: https://arxiv.org/abs/2501.02264 · HTML: https://mlsanity.com/paper/2501.02264/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 4 Jan 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 21 of 21)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving](https://mlsanity.com/paper/2005.03778/) (2020)
- [Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation](https://mlsanity.com/paper/2107.05399/) (2021)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control](https://mlsanity.com/paper/2312.03048/) (2023)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models](https://mlsanity.com/paper/2403.14291/) (2024)
- [Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances](https://mlsanity.com/paper/2412.16592/) (2024)

## Built on by (most cited first, 1 of 1)

- [Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting](https://mlsanity.com/paper/2603.16241/) (2026)

## Abstract (arXiv)

Semantic segmentation is a computer vision task where classification is performed at a pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been a surge in the use of synthetically generated data -- usually created using simulators or videogames -- which, in combination with domain adaptation methods, can effectively learn how to segment real data. Still, these datasets have a particular limitation: due to their closed-set nature, it is not possible to include novel classes without modifying the tool used to generate them, which is often not public. Concurrently, generative models have made remarkable progress, particularly with the introduction of diffusion models, enabling the creation of high-quality images from text prompts without additional supervision. In this work, we propose an unsupervised pipeline that leverages Stable Diffusion and Segment Anything Module to generate class examples with an associated segmentation mask, and a method to integrate generated cutouts for novel classes in semantic segmentation datasets, all with minimal user input. Our approach aims to improve the performance of unsupervised domain adaptation methods by introducing novel samples into the training data without modifications to the underlying algorithms. With our methods, we show how models can not only effectively learn how to segment novel classes, with an average performance of 51% IoU, but also reduce errors for other, already existing classes, reaching a higher performance level overall.