# SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1701.01081 · HTML: https://mlsanity.com/paper/1701.01081/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2017.

## Built on by (most cited first, 30 of 65)

- [Affordance Diffusion: Synthesizing Hand-Object Interactions](https://mlsanity.com/paper/2303.12538/) (2023)
- [DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling](https://mlsanity.com/paper/2105.12441/) (2021)
- [Human Hands as Probes for Interactive Object Understanding](https://mlsanity.com/paper/2112.09120/) (2021)
- [In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation](https://mlsanity.com/paper/2208.04464/) (2022)
- [TranSalNet: Towards perceptually relevant visual saliency prediction](https://mlsanity.com/paper/2110.03593/) (2021)
- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [Affordance Grounding from Demonstration Video to Target Image](https://mlsanity.com/paper/2303.14644/) (2023)
- [Learning Visual Affordance Grounding from Demonstration Videos](https://mlsanity.com/paper/2108.05675/) (2021)
- [ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Images](https://mlsanity.com/paper/2103.13922/) (2021)
- [ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery](https://mlsanity.com/paper/2112.08189/) (2021)
- [Controlling the World by Sleight of Hand](https://mlsanity.com/paper/2408.07147/) (2024)
- [Saliency in Augmented Reality](https://mlsanity.com/paper/2204.08308/) (2022)
- [Panoramic Vision Transformer for Saliency Detection in 360deg Videos](https://mlsanity.com/paper/2209.08956/) (2022)
- [Realistic Saliency Guided Image Enhancement](https://mlsanity.com/paper/2306.06092/) (2023)
- [SUM: Saliency Unification through Mamba for Visual Attention Modeling](https://mlsanity.com/paper/2406.17815/) (2024)
- [CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion](https://mlsanity.com/paper/2408.12009/) (2024)
- [INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2409.06210/) (2024)
- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [Energy-Based Generative Cooperative Saliency Prediction](https://mlsanity.com/paper/2106.13389/) (2021)
- [SALYPATH: A Deep-Based Architecture for visual attention prediction](https://mlsanity.com/paper/2107.00559/) (2021)
- [Audio-visual Saliency for Omnidirectional Videos](https://mlsanity.com/paper/2311.05190/) (2023)
- [UniAR: A Unified model for predicting human Attention and Responses on visual content](https://mlsanity.com/paper/2312.10175/) (2023)
- [How is Visual Attention Influenced by Text Guidance? Database and Model](https://mlsanity.com/paper/2404.07537/) (2024)
- [Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model](https://mlsanity.com/paper/2103.15438/) (2021)
- [Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks](https://mlsanity.com/paper/2505.02413/) (2025)
- [Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors](https://mlsanity.com/paper/2305.12380/) (2023)
- [Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm](https://mlsanity.com/paper/2312.03226/) (2023)
- [GazeFusion: Saliency-Guided Image Generation](https://mlsanity.com/paper/2407.04191/) (2024)
- [How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model](https://mlsanity.com/paper/2408.05411/) (2024)
- [Closed-Loop Transfer for Weakly-supervised Affordance Grounding](https://mlsanity.com/paper/2510.17384/) (2025)

## Abstract (arXiv)

We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Our results can be reproduced with the source code and trained models available at https://imatge-upc.github.io/saliency-salgan-2017/.