# FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

arXiv: https://arxiv.org/abs/2310.15160 · HTML: https://mlsanity.com/paper/2310.15160/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 75 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 30 of 65)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [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)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)

## Built on by (most cited first, 30 of 61)

- [DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control](https://mlsanity.com/paper/2312.03048/) (2023)
- [Large-Scale 3D Medical Image Pre-training with Geometric Context Priors](https://mlsanity.com/paper/2410.09890/) (2024)
- [Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging](https://mlsanity.com/paper/2502.14064/) (2025)
- [PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis](https://mlsanity.com/paper/2403.01852/) (2024)
- [SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis](https://mlsanity.com/paper/2311.03355/) (2023)
- [ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models](https://mlsanity.com/paper/2405.15199/) (2024)
- [Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation](https://mlsanity.com/paper/2410.02369/) (2024)
- [DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data](https://mlsanity.com/paper/2405.10185/) (2024)
- [FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis](https://mlsanity.com/paper/2406.01264/) (2024)
- [FairDiff: Fair Segmentation with Point-Image Diffusion](https://mlsanity.com/paper/2407.06250/) (2024)
- [Image Understanding Makes for A Good Tokenizer for Image Generation](https://mlsanity.com/paper/2411.04406/) (2024)
- [Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation](https://mlsanity.com/paper/2412.19080/) (2024)
- [Open-Vocabulary Camouflaged Object Segmentation](https://mlsanity.com/paper/2311.11241/) (2023)
- [Generative Enhancement for 3D Medical Images](https://mlsanity.com/paper/2403.12852/) (2024)
- [DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation](https://mlsanity.com/paper/2403.06168/) (2024)
- [Generative Active Learning for Long-tailed Instance Segmentation](https://mlsanity.com/paper/2406.02435/) (2024)
- [A Simple Background Augmentation Method for Object Detection with Diffusion Model](https://mlsanity.com/paper/2408.00350/) (2024)
- [Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation](https://mlsanity.com/paper/2411.10411/) (2024)
- [SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis](https://mlsanity.com/paper/2403.09638/) (2024)
- [ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation](https://mlsanity.com/paper/2311.17121/) (2023)
- [Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2503.17984/) (2025)
- [A Unified Image-Dense Annotation Generation Model for Underwater Scenes](https://mlsanity.com/paper/2503.21771/) (2025)
- [Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data](https://mlsanity.com/paper/2405.13779/) (2024)
- [Single Image, Any Face: Generalisable 3D Face Generation](https://mlsanity.com/paper/2409.16990/) (2024)
- [Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification](https://mlsanity.com/paper/2409.17091/) (2024)
- [Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs](https://mlsanity.com/paper/2503.12999/) (2025)
- [JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion](https://mlsanity.com/paper/2512.13014/) (2025)
- [On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models](https://mlsanity.com/paper/2402.11305/) (2024)
- [SynDiff-AD: Improving Semantic Segmentation and End-to-End Autonomous Driving with Synthetic Data from Latent Diffusion Models](https://mlsanity.com/paper/2411.16776/) (2024)
- [PathoPainter: Augmenting Histopathology Segmentation via Tumor-aware Inpainting](https://mlsanity.com/paper/2503.04634/) (2025)

## Abstract (arXiv)

Semantic segmentation has witnessed tremendous progress due to the proposal of various advanced network architectures. However, they are extremely hungry for delicate annotations to train, and the acquisition is laborious and unaffordable. Therefore, we present FreeMask in this work, which resorts to synthetic images from generative models to ease the burden of both data collection and annotation procedures. Concretely, we first synthesize abundant training images conditioned on the semantic masks provided by realistic datasets. This yields extra well-aligned image-mask training pairs for semantic segmentation models. We surprisingly observe that, solely trained with synthetic images, we already achieve comparable performance with real ones (e.g., 48.3 vs. 48.5 mIoU on ADE20K, and 49.3 vs. 50.5 on COCO-Stuff). Then, we investigate the role of synthetic images by joint training with real images, or pre-training for real images. Meantime, we design a robust filtering principle to suppress incorrectly synthesized regions. In addition, we propose to inequally treat different semantic masks to prioritize those harder ones and sample more corresponding synthetic images for them. As a result, either jointly trained or pre-trained with our filtered and re-sampled synthesized images, segmentation models can be greatly enhanced, e.g., from 48.7 to 52.0 on ADE20K. Code is available at https://github.com/LiheYoung/FreeMask.