We present GOOSE-M2F, a task-specific adaptation of Mask2Former for the GOOSE 2D Fine-Grained Semantic Segmentation (FGSS) Challenge at ICRA 2026. The GOOSE benchmark spans 64 fine-grained classes across unstructured outdoor terrain with a severely long-tailed distribution, where rare classes occupy fewer than 50 pixels per image. We extend the Swin-Large Mask2Former baseline with three targeted contributions: (1) 200 object queries to eliminate representational saturation; (2) a Feature Refinement Module (FRM) combining ASPP-lite and CBAM dual-attention; and (3) an Auxiliary Supervision Head that delivers direct per-pixel gradients for rare classes. A multi-stage training strategy pairs Distribution-Balanced loss, Rare-Class Copy-Paste augmentation, dynamic IoU-aware re-weighting, and EMA. At inference, a dense sliding-window engine with 2D Gaussian kernel blending and 4-scale TTA adds +10.57%. GOOSE-M2F achieves 70.08% Official Composite mIoU (63.55% fine, 76.61% coarse), placing 3rd on the GOOSE 2D FGSS leaderboard. Code and trained models are publicly available at GitHub: https://github.com/Aditya-Lingam-9000/GOOSE-M2F and Hugging Face: https://huggingface.co/XYZ9843/GOOSE-M2F.

翻译：我们提出GOOSE-M2F，一种针对ICRA 2026 GOOSE二维细粒度语义分割挑战赛定制的Mask2Former适配方法。GOOSE基准数据集涵盖非结构化户外地形中64个细粒度类别，呈现严重长尾分布，其中稀有类别每张图像中像素数不足50个。我们在Swin-Large Mask2Former基线基础上做出三项针对性改进：(1) 采用200个物体查询以消除表征饱和；(2) 提出融合ASPP-lite与CBAM双重注意力的特征精炼模块(FRM)；(3) 设计辅助监督头为稀有类别提供直接的逐像素梯度。多阶段训练策略结合了分布平衡损失、稀有类别复制-粘贴增强、动态IoU感知重加权及指数移动平均。推理阶段采用密集滑动窗口引擎（融合二维高斯核混合与4尺度测试时增强），带来+10.57%的性能提升。GOOSE-M2F在GOOSE二维细粒度语义分割排行榜上以70.08%官方综合平均交并比（细粒度63.55%，粗粒度76.61%）位列第三。代码与预训练模型已开源至GitHub：https://github.com/Aditya-Lingam-9000/GOOSE-M2F 及Hugging Face：https://huggingface.co/XYZ9843/GOOSE-M2F。