mlsanityData to 7 Oct 2026

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

arXiv 1701.01081 ↗First posted 4 Jan 2017cs.CVcited by 63

Not on the map. Why?

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/.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 9; 2023: 13; 2024: 11; 2025: 5; 2026: 6.

63 papers.

Sort:

By area:

  1. 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
  2. 2021DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modelingcited by 55
  3. 2021Human Hands as Probes for Interactive Object Understandingcited by 51
  4. 2022In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimationcited by 51
  5. 2021TranSalNet: Towards perceptually relevant visual saliency predictioncited by 44
  6. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  7. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  8. 2021Learning Visual Affordance Grounding from Demonstration Videoscited by 25
  9. 2021ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Imagescited by 23
  10. 2021ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgerycited by 20
  11. 2024Controlling the World by Sleight of Handcited by 19
  12. 2022Saliency in Augmented Realitycited by 17
38 more
  1. 2022Panoramic Vision Transformer for Saliency Detection in 360deg Videoscited by 15
  2. 2023Realistic Saliency Guided Image Enhancementcited by 14
  3. 2024SUM: Saliency Unification through Mamba for Visual Attention Modelingcited by 12
  4. 2024CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusioncited by 12
  5. 2024INTRA: Interaction Relationship-aware Weakly Supervised Affordance Groundingcited by 12
  6. 2021Instance-Level Relative Saliency Ranking with Graph Reasoningcited by 9
  7. 2021Energy-Based Generative Cooperative Saliency Predictioncited by 8
  8. 2021SALYPATH: A Deep-Based Architecture for visual attention predictioncited by 7
  9. 2023Audio-visual Saliency for Omnidirectional Videoscited by 7
  10. 2023UniAR: A Unified model for predicting human Attention and Responses on visual contentcited by 7
  11. 2024How is Visual Attention Influenced by Text Guidance? Database and Modelcited by 7
  12. 2021Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Modelcited by 6
  13. 2025Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networkscited by 5
  14. 2023Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictorscited by 4
  15. 2023Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigmcited by 4
  16. 2024GazeFusion: Saliency-Guided Image Generationcited by 4
  17. 2024How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Modelcited by 4
  18. 2025Closed-Loop Transfer for Weakly-supervised Affordance Groundingcited by 4
  19. 2021A Gated Fusion Network for Dynamic Saliency Predictioncited by 3
  20. 2025Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videoscited by 3
  21. 2021Where to look at the movies : Analyzing visual attention to understand movie editingcited by 2
  22. 2021ImportantAug: a data augmentation agent for speechcited by 2
  23. 2022A Probabilistic Time-Evolving Approach to Scanpath Predictioncited by 2
  24. 2023Spherical Vision Transformer for 360-degree Video Saliency Predictioncited by 2
  25. 2023Learning Saliency From Fixationscited by 2
  26. 2024Relevance for Human Robot Collaborationcited by 2
  27. 2025AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenescited by 2
  28. 2021Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videoscited by 1
  29. 2021A Simple and efficient deep Scanpath Predictioncited by 1
  30. 2021Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perceptioncited by 1
  31. 2022Clustered Saliency Predictioncited by 1
  32. 2023Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Biascited by 1
  33. 2024Learning Gaussian Representation for Eye Fixation Predictioncited by 1
  34. 2026SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptationcited by 1
  35. 2026Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based modelcited by 1
  36. 2021Noise-Aware Video Saliency Predictioncited by 0
  37. 2021Saliency for free: Saliency prediction as a side-effect of object recognitioncited by 0
  38. 2021Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentationcited by 0

50 most cited of 63 All 63 (JSON)