# Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding

arXiv: https://arxiv.org/abs/2409.08251 · HTML: https://mlsanity.com/paper/2409.08251/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)
- [Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2108.05565/) (2021)
- [Connecting Vision and Language with Localized Narratives](https://mlsanity.com/paper/1912.03098/) (2019)
- [Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation](https://mlsanity.com/paper/2003.08813/) (2020)
- [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)
- [Referring Image Segmentation via Cross-Modal Progressive Comprehension](https://mlsanity.com/paper/2010.00514/) (2020)
- [ReSTR: Convolution-free Referring Image Segmentation Using Transformers](https://mlsanity.com/paper/2203.16768/) (2022)
- [Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation](https://mlsanity.com/paper/2105.01839/) (2021)
- [Linguistic Structure Guided Context Modeling for Referring Image Segmentation](https://mlsanity.com/paper/2010.00515/) (2020)
- [Cross-Modal Progressive Comprehension for Referring Segmentation](https://mlsanity.com/paper/2105.07175/) (2021)
- [Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter](https://mlsanity.com/paper/2309.02773/) (2023)
- [Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation](https://mlsanity.com/paper/2105.06818/) (2021)
- [Panoptic Narrative Grounding](https://mlsanity.com/paper/2109.04988/) (2021)
- [Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation](https://mlsanity.com/paper/2303.06345/) (2023)
- [Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network](https://mlsanity.com/paper/2301.03160/) (2023)
- [PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding](https://mlsanity.com/paper/2208.05647/) (2022)
- [NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning](https://mlsanity.com/paper/2310.10975/) (2023)
- [Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding](https://mlsanity.com/paper/2311.01091/) (2023)
- [Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network](https://mlsanity.com/paper/2310.16616/) (2023)

## Built on by (most cited first, 4 of 4)

- [LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2501.08282/) (2025)
- [GS: Generative Segmentation via Label Diffusion](https://mlsanity.com/paper/2508.20020/) (2025)
- [3D-DRES: Detailed 3D Referring Expression Segmentation](https://mlsanity.com/paper/2603.02896/) (2026)
- [ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models](https://mlsanity.com/paper/2506.09740/) (2025)

## Abstract (arXiv)

Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous discriminative methods achieve only weak or coarse-grained alignment by panoptic segmentation pretraining or CLIP model adaptation. Given the recent progress of text-to-image Diffusion models, several works have shown their capability to achieve fine-grained image-text alignment through cross-attention maps and improved general segmentation performance. However, the direct use of phrase features as static prompts to apply frozen Diffusion models to the PNG task still suffers from a large task gap and insufficient vision-language interaction, yielding inferior performance. Therefore, we propose an Extractive-Injective Phrase Adapter (EIPA) bypass within the Diffusion UNet to dynamically update phrase prompts with image features and inject the multimodal cues back, which leverages the fine-grained image-text alignment capability of Diffusion models more sufficiently. In addition, we also design a Multi-Level Mutual Aggregation (MLMA) module to reciprocally fuse multi-level image and phrase features for segmentation refinement. Extensive experiments on the PNG benchmark show that our method achieves new state-of-the-art performance.