发表机构
Xidian University; Tsinghua University; Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（西安电子科技大学; 清华大学; 广东省人工智能与数字经济实验室（深圳））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对矿物图像分类的类别内差异与类别间混淆问题，提出基于Mona的RouteGraph-Mona方法，通过样本自适应路由与正则化提升性能，在多数据集及骨干网络上均优于Mona。
AI 中文摘要
矿物图像分类对地质勘探与资源开发至关重要，但因类别内外观差异大、类别间视觉相似度高而颇具挑战性。多认知视觉适配器（Mona）是一种面向视觉的参数高效适配器，仅微调少量参数即可适配预训练视觉模型。然而，Mona 静态聚合多尺度响应，限制了其适配样本特定尺度偏好及处理视觉相似矿物类别间混淆的能力。为解决该问题，我们提出 RouteGraph-Mona，一种构建于 Mona 之上的轻量路由空间正则化方法。具体而言，我们将 Mona 的静态多尺度聚合替换为样本自适应路由，生成的分支选择行为定义了紧凑的路由空间，可捕获每个图像的尺度偏好；随后我们用按类别划分的路由锚点与混淆加权间隔对生成的路由特征进行正则化，路由锚点鼓励类别一致的路由模式，间隔则促进视觉相似类别在路由空间中实现更大区分度。在三个公开矿物图像数据集上采用两种视觉骨干网络开展的实验表明，RouteGraph-Mona 在平均准确率上始终优于 Mona，且与代表性微调方法及矿物图像分类基线方法相比仍具竞争力。
英文摘要
Mineral image classification is important for geological exploration and resource development, but it remains challenging due to substantial intra-class variations in appearance and high inter-class visual similarity. Multi-cognitive Visual Adapter (Mona) is a vision-oriented parameter-efficient adapter that adapts pre-trained visual models by tuning only a few parameters. However, Mona statically aggregates responses from multiple scales, limiting its ability to accommodate sample-specific scale preferences and model confusion among visually similar mineral categories. To address this issue, we propose \textbf{RouteGraph-Mona}, a lightweight route-space regularization method built on Mona. Specifically, we replace Mona's static multi-scale aggregation with sample-adaptive routing. The resulting branch-selection behavior defines a compact routing space that captures each image's scale preferences. We then regularize the resulting routing signatures with class-wise route anchors and confusion-weighted margins. The route anchors encourage class-consistent routing patterns, while the margins promote greater separation between visually similar categories in the routing space. Experiments on three public mineral image datasets with two visual backbones show that RouteGraph-Mona consistently outperforms Mona in mean accuracy and remains competitive with representative fine-tuning methods and mineral image classification baselines.
