nnMNet提升火星地形语义分割精度，提供新基准与开源方案
nnMNet: Baseline for Martian Terrain Semantic Segmentation
- 用线性注意力+轻量卷积捕获全局上下文，降低计算开销
- 在三个数据集上达到86.61%~88.24% mIoU，刷新最佳性能
- 开源代码模型数据，推动火星视觉分析公平评估
语义分割对理解火星——太阳系中最像地球的行星——至关重要。然而，火星表面高度无序且复杂，导致像素级预测和细粒度标注困难。尽管深度学习取得进展，但该领域仍缺乏可复现、公开可用的基准和统一评测标准。本文提出nnMNet，一种专为火星地形语义分割设计的新基准模型。在nnWNet基础上，引入线性注意力以更好捕捉全局上下文，并采用轻量卷积减少计算开销。为融合局部与全局特征，提出空间感知融合模块（SAFB），增强多特性特征的整合。同时，通过整理和标准化三个高质量数据集，建立新基准。nnMNet在SynMars-TW、SynMars-Air和MarsScapes上分别取得86.61%、83.25%和88.24%的mIoU，达到新最优水平。代码、模型与数据已公开于https://github.com/dereklee0310/nnMNet。
原文摘要 · Abstract (English)
Semantic segmentation is a crucial task for understanding Mars, the most Earth-like planet in our solar system. However, it is challenging because the Martian surface is highly unstructured and complex, making accurate pixel-level prediction and fine-grained annotation difficult. Recent advancements in deep learning have introduced numerous methods and datasets to address these challenges. Nevertheless, the field lacks a robust, publicly available, and reproducible baseline, as well as a unified benchmark to facilitate fair evaluations. In this work, we present nnMNet, a new baseline model designed for Martian terrain semantic segmentation. Building upon nnWNet, we integrate linear attention to better capture global context and employ lightweight convolutions to reduce computational overhead. To bridge the gap between local and global representations, we introduce the Spatially-Aware Fusion Block (SAFB), which augments and combines features with diverse characteristics. Furthermore, we establish a new benchmark by curating and standardizing three high-quality datasets for thorough evaluation. nnMNet achieves new state-of-the-art 86.61%, 83.25%, and 88.24% mIoU on SynMars-TW, SynMars-Air, and MarsScapes, respectively. Our code, models, and datasets are publicly available at https://github.com/dereklee0310/nnMNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。