# Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization

arXiv: https://arxiv.org/abs/2012.02166 · HTML: https://mlsanity.com/paper/2012.02166/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer](https://mlsanity.com/paper/2403.14552/) (2024)
- [On the Faithfulness of Vision Transformer Explanations](https://mlsanity.com/paper/2404.01415/) (2024)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [Dynamic Attention-Guided Diffusion for Image Super-Resolution](https://mlsanity.com/paper/2308.07977/) (2023)
- [A Functional Information Perspective on Model Interpretation](https://mlsanity.com/paper/2206.05700/) (2022)
- [Learning a Weight Map for Weakly-Supervised Localization](https://mlsanity.com/paper/2111.14131/) (2021)
- [Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium](https://mlsanity.com/paper/2205.11109/) (2022)
- [Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance](https://mlsanity.com/paper/2312.14201/) (2023)
- [Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports](https://mlsanity.com/paper/2407.08610/) (2024)
- [Clinician-Friendly Foundation Models for Ophthalmic Image Diagnostics without Fine-Tuning or Technical Barriers](https://mlsanity.com/paper/2504.15928/) (2025)
- [Weakly Supervised Recovery of Semantic Attributes](https://mlsanity.com/paper/2103.11888/) (2021)
- [Explainability Guided Multi-Site COVID-19 CT Classification](https://mlsanity.com/paper/2103.13677/) (2021)
- [Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map](https://mlsanity.com/paper/2212.06299/) (2022)
- [XAI for Self-supervised Clustering of Wireless Spectrum Activity](https://mlsanity.com/paper/2305.10060/) (2023)
- [Model Guidance via Explanations Turns Image Classifiers into Segmentation Models](https://mlsanity.com/paper/2407.03009/) (2024)
- [EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanations](https://mlsanity.com/paper/2509.23585/) (2025)
- [Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random Crops](https://mlsanity.com/paper/2510.03606/) (2025)
- [Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design](https://mlsanity.com/paper/2511.18163/) (2025)
- [When Can We Trust Deep Neural Networks? Towards Reliable Industrial Deployment with an Interpretability Guide](https://mlsanity.com/paper/2604.19206/) (2026)

## Abstract (arXiv)

Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name em the saliency bias hypothesis. In this work, we integrate two lines of research: gradient-based methods and attribution-based methods, and develop an algorithm that provides per-class explainability. The algorithm back-projects the per pixel local influence, in a manner that is guided by the local attributions, while correcting for salient features that would otherwise bias the explanation. In an extensive battery of experiments, we demonstrate the ability of our methods to class-specific visualization, and not just the predicted label. Remarkably, the method obtains state of the art results in benchmarks that are commonly applied to gradient-based methods as well as in those that are employed mostly for evaluating attribution methods. Using a new unsupervised procedure, our method is also successful in demonstrating that self-supervised methods learn semantic information.