# SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation

arXiv: https://arxiv.org/abs/2604.25315 · HTML: https://mlsanity.com/paper/2604.25315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 28 Apr 2026.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [Reducing Overfitting in Deep Networks by Decorrelating Representations](https://mlsanity.com/paper/1511.06068/) (2015)
- [Decorrelated Batch Normalization](https://mlsanity.com/paper/1804.08450/) (2018)
- [On the Connection Between Adversarial Robustness and Saliency Map Interpretability](https://mlsanity.com/paper/1905.04172/) (2019)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [Gradient Regularization Improves Accuracy of Discriminative Models](https://mlsanity.com/paper/1712.09936/) (2017)
- [Saliency Learning: Teaching the Model Where to Pay Attention](https://mlsanity.com/paper/1902.08649/) (2019)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation](https://mlsanity.com/paper/2402.14611/) (2024)
- [SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training](https://mlsanity.com/paper/2311.05143/) (2023)
- [Integrated Gradient Correlation: a Dataset-wise Attribution Method](https://mlsanity.com/paper/2404.13910/) (2024)

## Abstract (arXiv)

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of this behavior lies in the geometry of learned representations: correlated feature dimensions diffuse attribution gradients across redundant directions, resulting in blurred and unreliable saliency maps. To address this issue, we identify feature correlation as a structural limitation of gradient-based interpretability and propose SaliencyDecor, a training framework that enforces feature decorrelation to improve attribution fidelity without modifying saliency methods or model architectures by reshaping the feature space toward orthogonality, our approach promotes more concentrated gradient flow and improves the fidelity of saliency-based explanations. SaliencyDecor jointly optimizes classification, prediction consistency under feature masking, and a decorrelation regularizer, requiring no architectural changes or inference-time overhead. Extensive experiments across multiple benchmarks and architectures demonstrate that our method produces substantially sharper and more object-focused saliency maps while simultaneously improving predictive performance, achieving accuracy gains across the datasets. These results establish our method as a principled mechanism for enhancing both interpretability and accuracy, challenging the conventional trade-off between explanation quality and model performance.