paper-with-me

홈 › Papers

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

2025-07-14 · Casey Wall, Longwei Wang, Rodrigue Rizk, KC Santosh 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.

📄 PDF Abstract BibTeX arXiv:2507.10846

Code (0)

등록된 구현이 없습니다.

Tasks

Polyp Segmentation

Similar Papers 제목 키워드 기반

Improved subsample-and-aggregate via the private modified winsorized mean

2025-01-23 · Kelly Ramsay, Dylan Spicker

We develop a univariate, differentially private mean estimator, called the private modified winsorized mean, designed to be used as the aggregator in subsample-and-aggregate. We demonstrate, via real data analysis, that …

Subspace Recovery in Winsorized PCA: Insights into Accuracy and Robustness

2025-02-23 · Sangil Han, Kyoowon Kim, Sungkyu Jung

In this paper, we explore the theoretical properties of subspace recovery using Winsorized Principal Component Analysis (WPCA), utilizing a common data transformation technique that caps extreme values to mitigate the im…

Learning Interpretable Logic Rules from Deep Vision Models

2025-03-13 · Chuqin Geng, Yuhe Jiang, Ziyu Zhao, Haolin Ye 외

We propose a general framework called VisionLogic to extract interpretable logic rules from deep vision models, with a focus on image classification tasks. Given any deep vision model that uses a fully connected layer as…

image-classificationImage Classification

Graphical Perception of Saliency-based Model Explanations

2024-06-11 · Yayan Zhao, MingWei Li, Matthew Berger

In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centere…

Experimental Designmodel

Differential privacy with dependent data

2025-11-23 · Valentin Roth, Marco Avella-Medina arxiv

Dependent data underlies many statistical studies in the social and health sciences, which often involve sensitive or private information. Differential privacy (DP) and in particular \textit{user-level} DP provide a natu…