# What Do Deep Saliency Models Learn about Visual Attention?

arXiv: https://arxiv.org/abs/2310.09679 · HTML: https://mlsanity.com/paper/2310.09679/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [Predicting the Driver's Focus of Attention: the DR(eye)VE Project](https://mlsanity.com/paper/1705.03854/) (2017)
- [Revisiting Video Saliency: A Large-scale Benchmark and a New Model](https://mlsanity.com/paper/1801.07424/) (2018)
- [DeepGaze II: Reading fixations from deep features trained on object recognition](https://mlsanity.com/paper/1610.01563/) (2016)
- [CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research](https://mlsanity.com/paper/1505.03581/) (2015)
- [DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations](https://mlsanity.com/paper/1510.02927/) (2015)
- [TranSalNet: Towards perceptually relevant visual saliency prediction](https://mlsanity.com/paper/2110.03593/) (2021)
- [Predicting Visual Importance Across Graphic Design Types](https://mlsanity.com/paper/2008.02912/) (2020)
- [Learning Visual Importance for Graphic Designs and Data Visualizations](https://mlsanity.com/paper/1708.02660/) (2017)
- [A Dilated Inception Network for Visual Saliency Prediction](https://mlsanity.com/paper/1904.03571/) (2019)
- [Understanding and Visualizing Deep Visual Saliency Models](https://mlsanity.com/paper/1903.02501/) (2019)
- [Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations](https://mlsanity.com/paper/2005.06583/) (2020)

## Built on by (most cited first, 4 of 4)

- [Modeling Saliency Dataset Bias](https://mlsanity.com/paper/2505.10169/) (2025)
- [Attend to Anything: Foundation Model for Unified Human Attention Modeling](https://mlsanity.com/paper/2606.03540/) (2026)
- [Incorporating Eye-Tracking Signals Into Multimodal Deep Visual Models For Predicting User Aesthetic Experience In Residential Interiors](https://mlsanity.com/paper/2601.16811/) (2026)
- [Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance](https://mlsanity.com/paper/2608.28218/) (2026)

## Abstract (arXiv)

In recent years, deep saliency models have made significant progress in predicting human visual attention. However, the mechanisms behind their success remain largely unexplained due to the opaque nature of deep neural networks. In this paper, we present a novel analytic framework that sheds light on the implicit features learned by saliency models and provides principled interpretation and quantification of their contributions to saliency prediction. Our approach decomposes these implicit features into interpretable bases that are explicitly aligned with semantic attributes and reformulates saliency prediction as a weighted combination of probability maps connecting the bases and saliency. By applying our framework, we conduct extensive analyses from various perspectives, including the positive and negative weights of semantics, the impact of training data and architectural designs, the progressive influences of fine-tuning, and common failure patterns of state-of-the-art deep saliency models. Additionally, we demonstrate the effectiveness of our framework by exploring visual attention characteristics in various application scenarios, such as the atypical attention of people with autism spectrum disorder, attention to emotion-eliciting stimuli, and attention evolution over time. Our code is publicly available at urlhttps://github.com/szzexpoi/saliencyanalysis.