# InvSeg: Test-Time Prompt Inversion for Semantic Segmentation

arXiv: https://arxiv.org/abs/2410.11473 · HTML: https://mlsanity.com/paper/2410.11473/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [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)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017)
- [Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion](https://mlsanity.com/paper/2308.12469/) (2023)
- [Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs](https://mlsanity.com/paper/2212.00785/) (2022)
- [Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision](https://mlsanity.com/paper/2301.09121/) (2023)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Open-vocabulary Object Segmentation with Diffusion Models](https://mlsanity.com/paper/2301.05221/) (2023)
- [Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter](https://mlsanity.com/paper/2309.02773/) (2023)
- [Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding](https://mlsanity.com/paper/2207.08455/) (2022)
- [ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency](https://mlsanity.com/paper/2302.10307/) (2023)
- [Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models](https://mlsanity.com/paper/2403.14291/) (2024)
- [Linear Semantics in Generative Adversarial Networks](https://mlsanity.com/paper/2104.00487/) (2021)
- [Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2404.00262/) (2024)

## Built on by (most cited first, 2 of 2)

- [FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.23323/) (2025)
- [Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives](https://mlsanity.com/paper/2607.26735/) (2026)

## Abstract (arXiv)

Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. However, a significant challenge arises due to the input distributional discrepancy between the context-rich sentences used for image generation and the isolated class names typically used in semantic segmentation. This discrepancy hinders diffusion models from capturing accurate visual-textual correlations. To solve this, we propose InvSeg, a test-time prompt inversion method that tackles open-vocabulary semantic segmentation by inverting image-specific visual context into text prompt embedding space, leveraging structure information derived from the diffusion model's reconstruction process to enrich text prompts so as to associate each class with a structure-consistent mask. Specifically, we introduce Contrastive Soft Clustering (CSC) to align derived masks with the image's structure information, softly selecting anchors for each class and calculating weighted distances to push inner-class pixels closer while separating inter-class pixels, thereby ensuring mask distinction and internal consistency. By incorporating sample-specific context, InvSeg learns context-rich text prompts in embedding space and achieves accurate semantic alignment across modalities. Experiments show that InvSeg achieves state-of-the-art performance on the PASCAL VOC, PASCAL Context and COCO Object datasets.