# Improving Deep Learning Interpretability by Saliency Guided Training

arXiv: https://arxiv.org/abs/2111.14338 · HTML: https://mlsanity.com/paper/2111.14338/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 68 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [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)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [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)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (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)

## Built on by (most cited first, 30 of 68)

- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning](https://mlsanity.com/paper/2209.09203/) (2022)
- [UNIREX: A Unified Learning Framework for Language Model Rationale Extraction](https://mlsanity.com/paper/2112.08802/) (2021)
- [Core Risk Minimization using Salient ImageNet](https://mlsanity.com/paper/2203.15566/) (2022)
- [Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods](https://mlsanity.com/paper/2210.07222/) (2022)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons](https://mlsanity.com/paper/2502.03391/) (2025)
- [Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning](https://mlsanity.com/paper/2212.08251/) (2022)
- [Learning with Explanation Constraints](https://mlsanity.com/paper/2303.14496/) (2023)
- [TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models](https://mlsanity.com/paper/2308.05985/) (2023)
- [Interpretability-Aware Vision Transformer](https://mlsanity.com/paper/2309.08035/) (2023)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [Bayesian Neural Networks with Domain Knowledge Priors](https://mlsanity.com/paper/2402.13410/) (2024)
- [Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach](https://mlsanity.com/paper/2405.06278/) (2024)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques](https://mlsanity.com/paper/2209.03798/) (2022)
- [Explainable AI: XAI-Guided Context-Aware Data Augmentation](https://mlsanity.com/paper/2506.03484/) (2025)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [MENTOR: Human Perception-Guided Pretraining for Increased Generalization](https://mlsanity.com/paper/2310.19545/) (2023)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)
- [Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task](https://mlsanity.com/paper/2412.03915/) (2024)
- [B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability](https://mlsanity.com/paper/2502.12992/) (2025)
- [AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations](https://mlsanity.com/paper/2511.18617/) (2025)
- [Improving Disease Classification Performance and Explainability of Deep Learning Models in Radiology with Heatmap Generators](https://mlsanity.com/paper/2207.00157/) (2022)
- [On Pitfalls of textitRemOve-And-Retrain: Data Processing Inequality Perspective](https://mlsanity.com/paper/2304.13836/) (2023)
- [Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations](https://mlsanity.com/paper/2307.04036/) (2023)
- [Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence](https://mlsanity.com/paper/2402.08466/) (2024)
- [X-SHIELD: Regularization for eXplainable Artificial Intelligence](https://mlsanity.com/paper/2404.02611/) (2024)

## Abstract (arXiv)

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in unfaithful feature attributions. In this paper, we tackle this issue and introduce a it saliency guided trainingprocedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model. Our saliency guided training procedure iteratively masks features with small and potentially noisy gradients while maximizing the similarity of model outputs for both masked and unmasked inputs. We apply the saliency guided training procedure to various synthetic and real data sets from computer vision, natural language processing, and time series across diverse neural architectures, including Recurrent Neural Networks, Convolutional Networks, and Transformers. Through qualitative and quantitative evaluations, we show that saliency guided training procedure significantly improves model interpretability across various domains while preserving its predictive performance.