# DeepRare: Generic Unsupervised Visual Attention Models

arXiv: https://arxiv.org/abs/2109.11439 · HTML: https://mlsanity.com/paper/2109.11439/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 23 Sep 2021.

## Builds on (most cited first, 9 of 9)

- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [A Deep Multi-Level Network for Saliency Prediction](https://mlsanity.com/paper/1609.01064/) (2016)
- [Contextual Encoder-Decoder Network for Visual Saliency Prediction](https://mlsanity.com/paper/1902.06634/) (2019)
- [Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations](https://mlsanity.com/paper/2005.06583/) (2020)
- [Visual Attention: Deep Rare Features](https://mlsanity.com/paper/2005.12073/) (2020)
- [Neural networks based EEG-Speech Models](https://mlsanity.com/paper/1612.05369/) (2016)
- [DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep Features of Convolutional Neural Nets](https://mlsanity.com/paper/1709.02495/) (2017)
- [Enhanced Factored Three-Way Restricted Boltzmann Machines for Speech Detection](https://mlsanity.com/paper/1611.00326/) (2016)
- [Semantic and Contrast-Aware Saliency](https://mlsanity.com/paper/1811.03736/) (2018)

## Built on by (most cited first, 1 of 1)

- [Nighttime Driver Behavior Prediction Using Taillight Signal Recognition via CNN-SVM Classifier](https://mlsanity.com/paper/2310.16706/) (2023)

## Abstract (arXiv)

Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning (DNNs) drastically improved the algorithms efficiency on the main benchmark datasets. However, DNN-based models are counter-intuitive: surprising or unusual data is by definition difficult to learn because of its low occurrence probability. In reality, DNN-based models mainly learn top-down features such as faces, text, people, or animals which usually attract human attention, but they have low efficiency in extracting surprising or unusual data in the images. In this paper, we propose a new visual attention model called DeepRare2021 (DR21) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms. This algorithm is an evolution of a previous version called DeepRare2019 (DR19) based on a common framework. DR21 1) does not need any training and uses the default ImageNet training, 2) is fast even on CPU, 3) is tested on four very different eye-tracking datasets showing that the DR21 is generic and is always in the within the top models on all datasets and metrics while no other model exhibits such a regularity and genericity. Finally DR21 4) is tested with several network architectures such as VGG16 (V16), VGG19 (V19) and MobileNetV2 (MN2) and 5) it provides explanation and transparency on which parts of the image are the most surprising at different levels despite the use of a DNN-based feature extractor. DeepRare2021 code can be found at https://github.com/numediart/VisualAttention-RareFamil}.