# Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency

arXiv: https://arxiv.org/abs/2410.16115 · HTML: https://mlsanity.com/paper/2410.16115/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Salient Object Detection: A Survey](https://mlsanity.com/paper/1411.5878/) (2014)
- [Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision](https://mlsanity.com/paper/1901.01151/) (2019)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Human-Aided Saliency Maps Improve Generalization of Deep Learning](https://mlsanity.com/paper/2105.03492/) (2021)
- [Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation](https://mlsanity.com/paper/2101.09321/) (2021)
- [Measuring Human Perception to Improve Handwritten Document Transcription](https://mlsanity.com/paper/1904.03734/) (2019)
- [Human Saliency-Driven Patch-based Matching for Interpretable Post-mortem Iris Recognition](https://mlsanity.com/paper/2208.03138/) (2022)
- [Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training](https://mlsanity.com/paper/2306.05527/) (2023)
- [Using Human Perception to Regularize Transfer Learning](https://mlsanity.com/paper/2211.07885/) (2022)

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

- [Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment](https://mlsanity.com/paper/2603.07462/) (2026)

## Abstract (arXiv)

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets, causing over-fitting and reducing the explainability. Recent advances have shown that guiding models to human-defined regions of saliency within individual images significantly increases performance and interpretability. Human-guided models also exhibit greater generalization capabilities, as coincidental dataset features are avoided. Results show that models trained with saliency incorporation display an increase in interpretability of up to 30% over models trained without saliency information. The collection of this saliency information, however, can be costly, laborious and in some cases infeasible. To address this limitation, we propose a combination strategy of saliency incorporation and active learning to reduce the human annotation data required by 80% while maintaining the interpretability and performance increase from human saliency. Extensive experimentation outlines the effectiveness of the proposed approach across five public datasets and six active learning criteria.