MedTokenBudget：用于皮肤镜图像分类的病灶保留令牌路由
MedTokenBudget: Lesion-Preserving Token Routing for Dermoscopic Image Classification
浏览论文内容
中文总结 AI 辅助
MedTokenBudget提出一种病灶感知令牌路由框架，通过LATS模块融合多种信号选择关键图像块，在保持病灶证据的同时提升皮肤镜图像分类性能。
中文摘要 AI 辅助
基于Vision Transformers构建的皮肤镜分类器对所有图像块进行统一处理，尽管诊断证据集中在病灶区域。现有的令牌剪枝方法使用通用显著性或相似性信号减少令牌，但很少询问保留的子集是否仍包含病灶。本文介绍了MedTokenBudget，一种受监督的后骨干令牌路由框架，当辅助病灶掩码可用时，学习构建紧凑的病灶富集表示。其病灶感知令牌评分（LATS）模块通过学习的评分器融合注意力熵、特征范数和局部特征对比度，然后在目标预算下路由前K个图像块。LATS通过预算课程学习、多样性正则化、注意力蒸馏和病灶掩码监督进行训练。训练后的路由器使用病灶保留率进行评估，该指标直接衡量有多少真实病灶证据在令牌预算中幸存。在ISIC 2019上，掩码监督的LATS在主要预算下始终优于Random和ToMe，同时保留显著更多的病灶块。提供代码以确保可复现性，完整的表格结果包含在补充材料中。
英文摘要
Dermoscopy classifiers built on Vision Transformers process all image patches uniformly, although diagnostic evidence is concentrated in the lesion region. Existing token pruning methods reduce tokens using generic saliency or similarity signals, but rarely ask whether the retained subset still contains the lesion. This paper introduces MedTokenBudget, a supervised post-backbone token routing framework that learns to construct compact lesion-enriched representations when auxiliary lesion masks are available. Its Lesion-Aware Token Scoring (LATS) module fuses attention entropy, feature norm, and local feature contrast through a learned scorer, then routes the top-$K$ patches under a target budget. LATS is trained with budget curriculum learning, diversity regularization, attention distillation, and lesion-mask supervision. The trained router is evaluated with a lesion retention rate that directly measures how much ground-truth lesion evidence survives the token budget. On ISIC 2019, mask-supervised LATS consistently outperforms Random and ToMe at headline budgets while retaining substantially more lesion patches. Code is provided for reproducibility, and complete tabulated results are included in the supplementary material.
发表机构
- University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。
