What Makes Synthetic Data Effective in Image Segmentation

• URL: http://arxiv.org/abs/2605.19289v1
• Date: Tue, 19 May 2026 03:07:04 GMT
• Title: What Makes Synthetic Data Effective in Image Segmentation
• Abstract summary: Synthetic data has emerged as a promising solution for visual understanding.<n>In this work, we conduct a systematic analysis of synthetic images from state-of-the-art diffusion models to uncover the factors governing their utility.<n>We propose SENSE, a unified framework that leverages flexible and scalable synthetic data to substantially enhance segmentation performance.
• Score: 35.90116236392466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remarkable photorealistic image synthesis, their potential in complex visual segmentation tasks remains underexplored. In this work, we conduct a systematic analysis of synthetic images from state-of-the-art diffusion models to uncover the factors governing their utility. In particular, synthetic images characterized by dense scene composition and fine instance fidelity demonstrate distinctive benefits, yielding significantly more discriminative spatial representations. Building on these insights, we propose SENSE, a unified framework that leverages flexible and scalable synthetic data to substantially enhance segmentation performance. Notably, SENSE is model-agnostic, compatible with diverse architectures (e.g., DPT and Mask2Former), and scales effectively across models with varying parameter capacities. Extensive experiments on Cityscapes, COCO, and ADE20K validate the effectiveness and generalization capability of our approach. Code is available at https://github.com/zhang0jhon/SENSE.

Related papers

• Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions [74.00222571094437]
  Blind Image Quality Assessment (BIQA) has advanced significantly through deep learning, but the scarcity of large-scale labeled datasets remains a challenge.<n>We make a key observation that representations learned from synthetic datasets often exhibit a discrete and clustered pattern that hinders regression performance.<n>We introduce a novel framework SynDR-IQA, which reshapes synthetic data distribution to enhance BIQA generalization.
  arXiv  Detail & Related papers  (2026-01-01T06:11:16Z)
• Enhancing Zero-Shot Pedestrian Attribute Recognition with Synthetic Data Generation: A Comparative Study with Image-To-Image Diffusion Models [4.151161561832882]
  Pedestrian Attribute Recognition (PAR) involves identifying various human attributes from images with applications in intelligent monitoring systems.<n>Recent advances in diffusion models have shown promise for generating diverse and realistic synthetic images.<n>This paper investigates the effectiveness of diffusion models in generating synthetic pedestrian images tailored to PAR tasks.
  arXiv  Detail & Related papers  (2025-09-02T10:12:53Z)
• Multi-focal Conditioned Latent Diffusion for Person Image Synthesis [59.113899155476005]
  The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation.<n>We propose a Multi-focal Conditioned Latent Diffusion (MCLD) method to address these limitations.<n>Our approach utilizes a multi-focal condition aggregation module, which effectively integrates facial identity and texture-specific information.
  arXiv  Detail & Related papers  (2025-03-19T20:50:10Z)
• Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms [0.9765507069335528]
  We propose novel $Gamma$-distribution Latent Denoising Diffusion Models (LDMs) to generate semantically guided synthetic cardiac ultrasound images. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks.
  arXiv  Detail & Related papers  (2024-09-28T14:50:50Z)
• Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
  We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability. We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images. Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
  arXiv  Detail & Related papers  (2024-03-28T22:25:05Z)
• Learning from Synthetic Data for Visual Grounding [55.21937116752679]
  We show that SynGround can improve the localization capabilities of off-the-shelf vision-and-language models.<n>Data generated with SynGround improves the pointing game accuracy of a pretrained ALBEF and BLIP models by 4.81% and 17.11% absolute percentage points, respectively.
  arXiv  Detail & Related papers  (2024-03-20T17:59:43Z)
• Improving the Effectiveness of Deep Generative Data [5.856292656853396]
  Training a model on purely synthetic images for downstream image processing tasks results in an undesired performance drop compared to training on real data. We propose a new taxonomy to describe factors contributing to this commonly observed phenomenon and investigate it on the popular CIFAR-10 dataset. Our method outperforms baselines on downstream classification tasks both in case of training on synthetic only (Synthetic-to-Real) and training on a mix of real and synthetic data.
  arXiv  Detail & Related papers  (2023-11-07T12:57:58Z)
• Generalizable Synthetic Image Detection via Language-guided Contrastive Learning [22.533225521726116]
  malevolent use of synthetic images, such as the dissemination of fake news or the creation of fake profiles, raises significant concerns regarding the authenticity of images.<n>We propose a simple yet very effective synthetic image detection method via a language-guided contrastive learning.<n>It is shown that our proposed LanguAge-guided SynThEsis Detection (LASTED) model achieves much improved generalizability to unseen image generation models.
  arXiv  Detail & Related papers  (2023-05-23T08:13:27Z)
• DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder [73.1010640692609]
  We propose a VQ-VAE architecture model with a diffusion decoder (DiVAE) to work as the reconstructing component in image synthesis. Our model achieves state-of-the-art results and generates more photorealistic images specifically.
  arXiv  Detail & Related papers  (2022-06-01T10:39:12Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.