# SynthSeg-Agents: Multi-Agent Synthetic Data Generation for Zero-Shot Weakly Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2512.15310 · HTML: https://mlsanity.com/paper/2512.15310/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02909/) (2022)
- [Token Contrast for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01267/) (2023)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)
- [SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2108.12517/) (2021)
- [Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.13765/) (2023)
- [Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.09760/) (2023)
- [SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11719/) (2024)
- [Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2407.10649/) (2024)
- [Image Augmentation Agent for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.20439/) (2024)

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

- [FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction](https://mlsanity.com/paper/2606.07645/) (2026)

## Abstract (arXiv)

Weakly Supervised Semantic Segmentation (WSSS) with image level labels aims to produce pixel level predictions without requiring dense annotations. While recent approaches have leveraged generative models to augment existing data, they remain dependent on real world training samples. In this paper, we introduce a novel direction, Zero Shot Weakly Supervised Semantic Segmentation (ZSWSSS), and propose SynthSeg Agents, a multi agent framework driven by Large Language Models (LLMs) to generate synthetic training data entirely without real images. SynthSeg Agents comprises two key modules, a Self Refine Prompt Agent and an Image Generation Agent. The Self Refine Prompt Agent autonomously crafts diverse and semantically rich image prompts via iterative refinement, memory mechanisms, and prompt space exploration, guided by CLIP based similarity and nearest neighbor diversity filtering. These prompts are then passed to the Image Generation Agent, which leverages Vision Language Models (VLMs) to synthesize candidate images. A frozen CLIP scoring model is employed to select high quality samples, and a ViT based classifier is further trained to relabel the entire synthetic dataset with improved semantic precision. Our framework produces high quality training data without any real image supervision. Experiments on PASCAL VOC 2012 and COCO 2014 show that SynthSeg Agents achieves competitive performance without using real training images. This highlights the potential of LLM driven agents in enabling cost efficient and scalable semantic segmentation.