# Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

arXiv: https://arxiv.org/abs/2308.12469 · HTML: https://mlsanity.com/paper/2308.12469/

## Key facts

- Cited by 131 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 23 Aug 2023.

## Placed in

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

## Builds on (most cited first, 30 of 35)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)

## Built on by (most cited first, 30 of 131)

- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal](https://mlsanity.com/paper/2406.16864/) (2024)
- [Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence](https://mlsanity.com/paper/2311.17034/) (2023)
- [Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation](https://mlsanity.com/paper/2312.10113/) (2023)
- [ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features](https://mlsanity.com/paper/2502.04320/) (2025)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023)
- [Exploiting Diffusion Prior for Generalizable Dense Prediction](https://mlsanity.com/paper/2311.18832/) (2023)
- [Interpretable Diffusion via Information Decomposition](https://mlsanity.com/paper/2310.07972/) (2023)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [SLiMe: Segment Like Me](https://mlsanity.com/paper/2309.03179/) (2023)
- [DragAPart: Learning a Part-Level Motion Prior for Articulated Objects](https://mlsanity.com/paper/2403.15382/) (2024)
- [Video Diffusion Models: A Survey](https://mlsanity.com/paper/2405.03150/) (2024)
- [UniGS: Unified Representation for Image Generation and Segmentation](https://mlsanity.com/paper/2312.01985/) (2023)
- [Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models](https://mlsanity.com/paper/2403.14291/) (2024)
- [Conditional Image Synthesis with Diffusion Models: A Survey](https://mlsanity.com/paper/2409.19365/) (2024)
- [DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut](https://mlsanity.com/paper/2406.02842/) (2024)
- [Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features](https://mlsanity.com/paper/2410.03558/) (2024)
- [Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2509.18096/) (2025)
- [MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model](https://mlsanity.com/paper/2312.04802/) (2023)
- [Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval](https://mlsanity.com/paper/2405.18025/) (2024)
- [ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction](https://mlsanity.com/paper/2407.07077/) (2024)
- [TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation](https://mlsanity.com/paper/2503.07050/) (2025)
- [Unsupervised Keypoints from Pretrained Diffusion Models](https://mlsanity.com/paper/2312.00065/) (2023)
- [DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild](https://mlsanity.com/paper/2405.19996/) (2024)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model](https://mlsanity.com/paper/2407.05352/) (2024)
- [Object Pose Estimation via the Aggregation of Diffusion Features](https://mlsanity.com/paper/2403.18791/) (2024)
- [Augmented Object Intelligence with XR-Objects](https://mlsanity.com/paper/2404.13274/) (2024)
- [MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation](https://mlsanity.com/paper/2403.11194/) (2024)

## Abstract (arXiv)

Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU. The project page is at urlhttps://sites.google.com/view/diffseg/home.