arXiv cs.AI· Md Shohanoor Rahman, Md Hasibul Islam, Md Kishor Morol, Dip Nandi, Tze Hui Liew·· 5 小时前AI 评分35
用扩散反事实与匹配阳性对照测试黑色素瘤分类器的概念级审计
Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls
AI 导读
研究者基于七个 7-point checklist 概念构建扩散模型反事实审计，检验黑色素瘤分类器的概念级解释，并用已知目标的匹配阳性对照与置换标签分类器作验证。
正文 · 原文
Abstract:Concept-based explanations of melanoma classifiers are rarely tested against controls with known targets. We built a counterfactual audit from a diffusion model conditioned on seven 7-point checklist concepts and tested it with such controls. Colour-calibrated start noise reduced colour outliers from 78.5-84.8\% to 6.6-13.3\%. Four of seven knobs were target-dominant but also changed other concepts. Quartile-based positive controls were confounded, and the audit failed its pre-specified rule. It recovered the targets of all 16 controls matched on the generator's pseudo-labels and of 12 of 12 controls labelled by a second evaluator, for three concepts; concept activation vectors recovered fewer (11 of 16). In 18 permuted-label classifiers, significant sweep responses and target rankings also arose, whereas standardised effect margins separated the controls from these null classifiers. The pigmentation sweep raised the melanoma logit in 15 of 15 ISIC 2020 classifiers (+3.12 on average) and 6 of 6 HAM10000 classifiers (+4.01), about four times the null response in scale-free units; the regression effect did not transfer. An exploratory decomposition, evaluated against the controls, suggested that knob cross-talk partly hides vascular responses. Matched controls and null classifiers are practical checks of concept audits.
| Comments: | 25 pages, 7 figures, 9 tables. Under review at Scientific Reports. Code and data at this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.02119 [cs.CV] |
| (or arXiv:2611.02119v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02119 arXiv-issued DOI via DataCite |
Submission history
From: Md Shohanoor Rahman [view email]
[v1]
Sun, 1 Nov 2026 18:48:33 UTC (356 KB)
[v2]
Wed, 4 Nov 2026 06:25:05 UTC (359 KB)
来源：arXiv cs.AI · arxiv.org