# Saliency for free: Saliency prediction as a side-effect of object recognition

arXiv: https://arxiv.org/abs/2107.09628 · HTML: https://mlsanity.com/paper/2107.09628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 20 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [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)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [What do different evaluation metrics tell us about saliency models?](https://mlsanity.com/paper/1604.03605/) (2016)
- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [SalGAN: Visual Saliency Prediction with Generative Adversarial Networks](https://mlsanity.com/paper/1701.01081/) (2017)
- [DeepGaze II: Reading fixations from deep features trained on object recognition](https://mlsanity.com/paper/1610.01563/) (2016)
- [A Deep Multi-Level Network for Saliency Prediction](https://mlsanity.com/paper/1609.01064/) (2016)
- [CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research](https://mlsanity.com/paper/1505.03581/) (2015)
- [Deep Contrast Learning for Salient Object Detection](https://mlsanity.com/paper/1603.01976/) (2016)
- [Shallow and Deep Convolutional Networks for Saliency Prediction](https://mlsanity.com/paper/1603.00845/) (2016)
- [Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data](https://mlsanity.com/paper/1808.00262/) (2018)
- [Online Visual Place Recognition via Saliency Re-identification](https://mlsanity.com/paper/2007.14549/) (2020)
- [Reconciling saliency and object center-bias hypotheses in explaining free-viewing fixations](https://mlsanity.com/paper/1503.08853/) (2015)
- [Top-Down Saliency Detection Driven by Visual Classification](https://mlsanity.com/paper/1709.05307/) (2017)
- [Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains](https://mlsanity.com/paper/2007.12562/) (2020)
- [SID4VAM: A Benchmark Dataset with Synthetic Images for Visual Attention Modeling](https://mlsanity.com/paper/1910.13066/) (2019)
- [Psychophysical evaluation of individual low-level feature influences on visual attention](https://mlsanity.com/paper/1811.06458/) (2018)

## Abstract (arXiv)

Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth saliency maps for training which are usually achieved via eyetracking experiments. In the current paper, we demonstrate that saliency maps can be generated as a side-effect of training an object recognition deep neural network that is endowed with a saliency branch. Such a network does not require any ground-truth saliency maps for training.Extensive experiments carried out on both real and synthetic saliency datasets demonstrate that our approach is able to generate accurate saliency maps, achieving competitive results on both synthetic and real datasets when compared to methods that do require ground truth data.