# Implicit Saliency in Deep Neural Networks

arXiv: https://arxiv.org/abs/2008.01874 · HTML: https://mlsanity.com/paper/2008.01874/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Introspective Learning : A Two-Stage Approach for Inference in Neural Networks](https://mlsanity.com/paper/2209.08425/) (2022)
- [Extracting Causal Visual Features for Limited label Classification](https://mlsanity.com/paper/2103.12322/) (2021)
- [Explanatory Paradigms in Neural Networks](https://mlsanity.com/paper/2202.11838/) (2022)
- [Open-Set Recognition with Gradient-Based Representations](https://mlsanity.com/paper/2206.08229/) (2022)
- [VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability](https://mlsanity.com/paper/2406.00573/) (2024)
- [Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks](https://mlsanity.com/paper/2302.05776/) (2023)
- [Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks](https://mlsanity.com/paper/2405.13758/) (2024)
- [Explainable Machine Learning for Hydrocarbon Prospect Risking](https://mlsanity.com/paper/2212.07563/) (2022)

## Abstract (arXiv)

In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency. We term this as implicit saliency in deep neural networks. We calculate this implicit saliency using expectancy-mismatch hypothesis in an unsupervised fashion. Our experiments show that extracting saliency in this fashion provides comparable performance when measured against the state-of-art supervised algorithms. Additionally, the robustness outperforms those algorithms when we add large noise to the input images. Also, we show that semantic features contribute more than low-level features for human visual saliency detection.