# Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models

arXiv: https://arxiv.org/abs/2308.16777 · HTML: https://mlsanity.com/paper/2308.16777/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 50 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [PolyFormer: Referring Image Segmentation as Sequential Polygon Generation](https://mlsanity.com/paper/2302.07387/) (2023)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [VLT: Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2210.15871/) (2022)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)

## Built on by (most cited first, 30 of 33)

- [Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding](https://mlsanity.com/paper/2503.06287/) (2025)
- [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models](https://mlsanity.com/paper/2403.14291/) (2024)
- [Learning Visual Grounding from Generative Vision and Language Model](https://mlsanity.com/paper/2407.14563/) (2024)
- [MC2: Multi-concept Guidance for Customized Multi-concept Generation](https://mlsanity.com/paper/2404.05268/) (2024)
- [IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis](https://mlsanity.com/paper/2503.00936/) (2025)
- [Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentation](https://mlsanity.com/paper/2312.08007/) (2023)
- [Text Augmented Spatial-aware Zero-shot Referring Image Segmentation](https://mlsanity.com/paper/2310.18049/) (2023)
- [Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning](https://mlsanity.com/paper/2410.03321/) (2024)
- [ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction](https://mlsanity.com/paper/2407.07077/) (2024)
- [VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models](https://mlsanity.com/paper/2403.05438/) (2024)
- [Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation](https://mlsanity.com/paper/2504.00356/) (2025)
- [Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model](https://mlsanity.com/paper/2407.05352/) (2024)
- [Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation](https://mlsanity.com/paper/2407.07412/) (2024)
- [Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision](https://mlsanity.com/paper/2410.08209/) (2024)
- [JOG3R: Towards 3D-Consistent Video Generators](https://mlsanity.com/paper/2501.01409/) (2025)
- [Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting](https://mlsanity.com/paper/2512.24702/) (2025)
- [Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques](https://mlsanity.com/paper/2410.06719/) (2024)
- [GS: Generative Segmentation via Label Diffusion](https://mlsanity.com/paper/2508.20020/) (2025)
- [RefAM: Attention Magnets for Zero-Shot Referral Segmentation](https://mlsanity.com/paper/2509.22650/) (2025)
- [In-Situ Tweedie Discrete Diffusion Models](https://mlsanity.com/paper/2510.01047/) (2025)
- [ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models](https://mlsanity.com/paper/2503.19902/) (2025)
- [Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review](https://mlsanity.com/paper/2505.07866/) (2025)
- [AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos](https://mlsanity.com/paper/2603.07758/) (2026)
- [RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation](https://mlsanity.com/paper/2603.14880/) (2026)
- [Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation](https://mlsanity.com/paper/2604.07916/) (2026)
- [Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation](https://mlsanity.com/paper/2605.13122/) (2026)
- [Vision Harnessing Agent for Open Ad-hoc Segmentation](https://mlsanity.com/paper/2605.19410/) (2026)
- [ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning](https://mlsanity.com/paper/2312.01682/) (2023)

## Abstract (arXiv)

Zero-shot referring image segmentation is a challenging task because it aims to find an instance segmentation mask based on the given referring descriptions, without training on this type of paired data. Current zero-shot methods mainly focus on using pre-trained discriminative models (e.g., CLIP). However, we have observed that generative models (e.g., Stable Diffusion) have potentially understood the relationships between various visual elements and text descriptions, which are rarely investigated in this task. In this work, we introduce a novel Referring Diffusional segmentor (Ref-Diff) for this task, which leverages the fine-grained multi-modal information from generative models. We demonstrate that without a proposal generator, a generative model alone can achieve comparable performance to existing SOTA weakly-supervised models. When we combine both generative and discriminative models, our Ref-Diff outperforms these competing methods by a significant margin. This indicates that generative models are also beneficial for this task and can complement discriminative models for better referring segmentation. Our code is publicly available at https://github.com/kodenii/Ref-Diff.