# A Deep Multi-Level Network for Saliency Prediction

arXiv: https://arxiv.org/abs/1609.01064 · HTML: https://mlsanity.com/paper/1609.01064/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2016.

## Built on by (most cited first, 30 of 54)

- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation](https://mlsanity.com/paper/2107.10189/) (2021)
- [TranSalNet: Towards perceptually relevant visual saliency prediction](https://mlsanity.com/paper/2110.03593/) (2021)
- [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)
- [TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction](https://mlsanity.com/paper/2301.02315/) (2023)
- [Grounded Affordance from Exocentric View](https://mlsanity.com/paper/2208.13196/) (2022)
- [Spatio-Temporal Self-Attention Network for Video Saliency Prediction](https://mlsanity.com/paper/2108.10696/) (2021)
- [Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding](https://mlsanity.com/paper/2303.09706/) (2023)
- [Saliency in Augmented Reality](https://mlsanity.com/paper/2204.08308/) (2022)
- [Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark](https://mlsanity.com/paper/2212.09381/) (2022)
- [Rectify ViT Shortcut Learning by Visual Saliency](https://mlsanity.com/paper/2206.08567/) (2022)
- [INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2409.06210/) (2024)
- [MAAD: A Model and Dataset for "Attended Awareness" in Driving](https://mlsanity.com/paper/2110.08610/) (2021)
- [SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks](https://mlsanity.com/paper/2112.03731/) (2021)
- [Attention mechanisms and deep learning for machine vision: A survey of the state of the art](https://mlsanity.com/paper/2106.07550/) (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)
- [How is Visual Attention Influenced by Text Guidance? Database and Model](https://mlsanity.com/paper/2404.07537/) (2024)
- [Agentic Retoucher for Text-To-Image Generation](https://mlsanity.com/paper/2601.02046/) (2026)
- [Data Augmentation via Latent Diffusion for Saliency Prediction](https://mlsanity.com/paper/2409.07307/) (2024)
- [Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization](https://mlsanity.com/paper/2305.02536/) (2023)
- [Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm](https://mlsanity.com/paper/2312.03226/) (2023)
- [Learning User Embeddings from Human Gaze for Personalised Saliency Prediction](https://mlsanity.com/paper/2403.13653/) (2024)
- [How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model](https://mlsanity.com/paper/2408.05411/) (2024)
- [SalM2: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention](https://mlsanity.com/paper/2502.16214/) (2025)
- [Closed-Loop Transfer for Weakly-supervised Affordance Grounding](https://mlsanity.com/paper/2510.17384/) (2025)
- [AD-Lite Net: A Lightweight and Concatenated CNN Model for Alzheimer's Detection from MRI Images](https://mlsanity.com/paper/2409.08170/) (2024)
- [Modeling Object Dissimilarity for Deep Saliency Prediction](https://mlsanity.com/paper/2104.03864/) (2021)
- [Reinforcement Learning for Predicting Traffic Accidents](https://mlsanity.com/paper/2212.04677/) (2022)

## Abstract (arXiv)

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural Network (CNN). Our model is composed of three main blocks: a feature extraction CNN, a feature encoding network, that weights low and high level feature maps, and a prior learning network. We compare our solution with state of the art saliency models on two public benchmarks datasets. Results show that our model outperforms under all evaluation metrics on the SALICON dataset, which is currently the largest public dataset for saliency prediction, and achieves competitive results on the MIT300 benchmark.