# Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization

arXiv: https://arxiv.org/abs/2202.00232 · HTML: https://mlsanity.com/paper/2202.00232/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images](https://mlsanity.com/paper/1808.08114/) (2018)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [COVID-19 Image Data Collection](https://mlsanity.com/paper/2003.11597/) (2020)
- [BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients](https://mlsanity.com/paper/2006.01174/) (2020)
- [Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization](https://mlsanity.com/paper/2007.14895/) (2020)
- [A Critic Evaluation of Methods for COVID-19 Automatic Detection from X-Ray Images](https://mlsanity.com/paper/2004.12823/) (2020)
- [Comparing Different Deep Learning Architectures for Classification of Chest Radiographs](https://mlsanity.com/paper/2002.08991/) (2020)
- [Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis](https://mlsanity.com/paper/2112.12349/) (2021)
- [Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images](https://mlsanity.com/paper/2009.09780/) (2020)
- [The surprising impact of mask-head architecture on novel class segmentation](https://mlsanity.com/paper/2104.00613/) (2021)
- [Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification](https://mlsanity.com/paper/1809.08264/) (2018)
- [A Deep Convolutional Neural Network for COVID-19 Detection Using Chest X-Rays](https://mlsanity.com/paper/2005.01578/) (2020)
- [Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models](https://mlsanity.com/paper/2001.01037/) (2020)
- [COVID-19 detection using chest X-rays: is lung segmentation important for generalization?](https://mlsanity.com/paper/2104.06176/) (2021)

## Built on by (most cited first, 25 of 25)

- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [RadGPT: Constructing 3D Image-Text Tumor Datasets](https://mlsanity.com/paper/2501.04678/) (2025)
- [Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?](https://mlsanity.com/paper/2411.03670/) (2024)
- [Abstractive Text Summarization: State of the Art, Challenges, and Improvements](https://mlsanity.com/paper/2409.02413/) (2024)
- [Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks](https://mlsanity.com/paper/2510.14803/) (2025)
- [Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview](https://mlsanity.com/paper/2503.08420/) (2025)
- [Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation](https://mlsanity.com/paper/2410.23693/) (2024)
- [BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision](https://mlsanity.com/paper/2406.19148/) (2024)
- [Faster ISNet for Background Bias Mitigation on Deep Neural Networks](https://mlsanity.com/paper/2401.08409/) (2024)
- [Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition](https://mlsanity.com/paper/2403.05754/) (2024)
- [BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices](https://mlsanity.com/paper/2409.17093/) (2024)
- [PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Models](https://mlsanity.com/paper/2505.10515/) (2025)
- [Urban Representation Learning for Fine-grained Economic Mapping: A Semi-supervised Graph-based Approach](https://mlsanity.com/paper/2505.11645/) (2025)
- [CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies](https://mlsanity.com/paper/2512.16700/) (2025)
- [Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning](https://mlsanity.com/paper/2407.09788/) (2024)
- [Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)](https://mlsanity.com/paper/2510.00475/) (2025)
- [PLATONT: Learning a Platonic Representation for Unified Network Tomography](https://mlsanity.com/paper/2511.15251/) (2025)
- [Physical Knot Classification Beyond Accuracy: A Benchmark and Diagnostic Study](https://mlsanity.com/paper/2603.23286/) (2026)
- [When Can We Trust Deep Neural Networks? Towards Reliable Industrial Deployment with an Interpretability Guide](https://mlsanity.com/paper/2604.19206/) (2026)
- [AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning](https://mlsanity.com/paper/2605.28809/) (2026)
- [ReMoDEx: A Local-to-Global Relevance-Based Model Decision Explainability Framework for large-Scale Image Datasets](https://mlsanity.com/paper/2607.06889/) (2026)
- [Report Supervision](https://mlsanity.com/paper/2608.27668/) (2026)
- [IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition](https://mlsanity.com/paper/2609.03985/) (2026)

## Abstract (arXiv)

Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias. They can influence the classifier's decisions, causing shortcut learning (Clever Hans effect). The phenomenon generates deep neural networks (DNNs) that perform well on standard evaluation datasets but generalize poorly to real-world data. Layer-wise Relevance Propagation (LRP) explains DNNs' decisions. Here, we show that the optimization of LRP heatmaps can minimize the background bias influence on deep classifiers, hindering shortcut learning. By not increasing run-time computational cost, the approach is light and fast. Furthermore, it applies to virtually any classification architecture. After injecting synthetic bias in images' backgrounds, we compared our approach (dubbed ISNet) to eight state-of-the-art DNNs, quantitatively demonstrating its superior robustness to background bias. Mixed datasets are common for COVID-19 and tuberculosis classification with chest X-rays, fostering background bias. By focusing on the lungs, the ISNet reduced shortcut learning. Thus, its generalization performance on external (out-of-distribution) test databases significantly surpassed all implemented benchmark models.