# Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization

arXiv: https://arxiv.org/abs/2507.10846 · HTML: https://mlsanity.com/paper/2507.10846/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 30 of 39)

- [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)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [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)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (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)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)

## Built on by (most cited first, 10 of 10)

- [Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness](https://mlsanity.com/paper/2509.11355/) (2025)
- [Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence](https://mlsanity.com/paper/2510.23524/) (2025)
- [Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks](https://mlsanity.com/paper/2601.00968/) (2026)
- [Learning to Select Like Humans: Explainable Active Learning for Medical Imaging](https://mlsanity.com/paper/2602.13308/) (2026)
- [Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition](https://mlsanity.com/paper/2604.22390/) (2026)
- [Explainable Novel Category Discovery in Semantic Concept Space](https://mlsanity.com/paper/2607.04548/) (2026)
- [AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models](https://mlsanity.com/paper/2602.16042/) (2026)
- [MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models](https://mlsanity.com/paper/2603.20074/) (2026)
- [Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs](https://mlsanity.com/paper/2607.07903/) (2026)
- [Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI](https://mlsanity.com/paper/2608.05258/) (2026)

## Abstract (arXiv)

Interpreting Convolutional Neural Networks (CNNs) is critical for safety-sensitive applications such as healthcare and autonomous systems. Popular visual explanation methods like Grad-CAM use a single convolutional layer, potentially missing multi-scale cues and producing unstable saliency maps. We introduce Winsor-CAM, a single-pass gradient-based method that aggregates Grad-CAM maps from all convolutional layers and applies percentile-based Winsorization to attenuate outlier contributions. A user-controllable percentile parameter p enables semantic-level tuning from low-level textures to high-level object patterns. We evaluate Winsor-CAM on six CNN architectures using PASCAL VOC 2012 and PolypGen, comparing localization (IoU, center-of-mass distance) and fidelity (insertion/deletion AUC) against seven baselines including Grad-CAM, Grad-CAM++, LayerCAM, ScoreCAM, AblationCAM, ShapleyCAM, and FullGrad. On DenseNet121 with a subset of Pascal VOC 2012, Winsor-CAM achieves 46.8% IoU and 0.059 CoM distance versus 39.0% and 0.074 for Grad-CAM, with improved insertion AUC (0.656 vs. 0.623) and deletion AUC (0.197 vs. 0.242). Notably, even the worst-performing fixed p-value configuration outperforms FullGrad across all metrics. An ablation study confirms that incorporating earlier layers improves localization. Similar evaluation on PolypGen polyp segmentation further validates Winsor-CAM's effectiveness in medical imaging contexts. Winsor-CAM provides an efficient, robust, and human-tunable explanation tool for expert-in-the-loop analysis.