# Synthetic Data Supervised Salient Object Detection

arXiv: https://arxiv.org/abs/2210.13835 · HTML: https://mlsanity.com/paper/2210.13835/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 30 of 38)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [F3Net: Fusion, Feedback and Focus for Salient Object Detection](https://mlsanity.com/paper/1911.11445/) (2019)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Meta-Sim: Learning to Generate Synthetic Datasets](https://mlsanity.com/paper/1904.11621/) (2019)
- [Weakly-Supervised Salient Object Detection via Scribble Annotations](https://mlsanity.com/paper/2003.07685/) (2020)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Unsupervised Object Segmentation by Redrawing](https://mlsanity.com/paper/1905.13539/) (2019)
- [Explorations in Homeomorphic Variational Auto-Encoding](https://mlsanity.com/paper/1807.04689/) (2018)
- [Emergence of Object Segmentation in Perturbed Generative Models](https://mlsanity.com/paper/1905.12663/) (2019)
- [Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence](https://mlsanity.com/paper/2012.04404/) (2020)
- [Semi-Supervised Video Salient Object Detection Using Pseudo-Labels](https://mlsanity.com/paper/1908.04051/) (2019)
- [Labels4Free: Unsupervised Segmentation using StyleGAN](https://mlsanity.com/paper/2103.14968/) (2021)
- [Object Segmentation Without Labels with Large-Scale Generative Models](https://mlsanity.com/paper/2006.04988/) (2020)
- [Navigating the GAN Parameter Space for Semantic Image Editing](https://mlsanity.com/paper/2011.13786/) (2020)
- [Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground](https://mlsanity.com/paper/1803.06091/) (2018)
- [Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models](https://mlsanity.com/paper/2105.08127/) (2021)
- [Multi-source weak supervision for saliency detection](https://mlsanity.com/paper/1904.00566/) (2019)

## Built on by (most cited first, 15 of 15)

- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control](https://mlsanity.com/paper/2312.03048/) (2023)
- [HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Models](https://mlsanity.com/paper/2306.12085/) (2023)
- [Dataset Enhancement with Instance-Level Augmentations](https://mlsanity.com/paper/2406.08249/) (2024)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [Object Segmentation by Mining Cross-Modal Semantics](https://mlsanity.com/paper/2305.10469/) (2023)
- [DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation](https://mlsanity.com/paper/2308.01127/) (2023)
- [Few-shot Geometry-Aware Keypoint Localization](https://mlsanity.com/paper/2303.17216/) (2023)
- [S3OD: Towards Generalizable Salient Object Detection with Synthetic Data](https://mlsanity.com/paper/2510.21605/) (2025)
- [VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset](https://mlsanity.com/paper/2407.18245/) (2024)
- [Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions](https://mlsanity.com/paper/2409.15927/) (2024)
- [Image compositing is all you need for data augmentation](https://mlsanity.com/paper/2502.13936/) (2025)
- [Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning](https://mlsanity.com/paper/2510.04770/) (2025)
- [MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation](https://mlsanity.com/paper/2603.19575/) (2026)

## Abstract (arXiv)

Although deep salient object detection (SOD) has achieved remarkable progress, deep SOD models are extremely data-hungry, requiring large-scale pixel-wise annotations to deliver such promising results. In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model. Its contribution is three-fold. 1) Our proposed diffusion embedding network can address the manifold mismatch and is tractable for the latent code generation, better matching with the ImageNet latent space. 2) For the first time, our proposed few-shot saliency mask generator can synthesize infinite accurate image synchronized saliency masks with a few labeled data. 3) Our proposed quality-aware discriminator can select highquality synthesized image-mask pairs from noisy synthetic data pool, improving the quality of synthetic data. For the first time, our SODGAN tackles SOD with synthetic data directly generated from the generative model, which opens up a new research paradigm for SOD. Extensive experimental results show that the saliency model trained on synthetic data can achieve 98.4% F-measure of the saliency model trained on the DUTS-TR. Moreover, our approach achieves a new SOTA performance in semi/weakly-supervised methods, and even outperforms several fully-supervised SOTA methods. Code is available at https://github.com/wuzhenyubuaa/SODGAN