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: \href{https://github.com/Aditya-Lingam-9000/GOOSE-M2F}{Github GOOSE-M2F Code} and \href{https://huggingface.co/XYZ9843/GOOSE-M2F}{Hugging Face GOOSE-M2F}.

翻译：我们提出了GOOSE-M2F，这是Mask2Former针对ICRA~2026 GOOSE 2D细粒度语义分割挑战的任务特定适配版本。GOOSE基准测试涵盖非结构化户外地形中64个细粒度类别，呈现严重的长尾分布，其中稀有类别每张图像中像素数少于50个。我们通过三项针对性贡献扩展了Swin-Large Mask2Former基线：(1)200个对象查询以消除表示饱和；(2)结合ASPP-lite与CBAM双重注意力的特征精化模块；(3)为稀有类别提供直接逐像素梯度的辅助监督头。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感知重加权以及EMA。推理阶段，采用带2D高斯核融合的密集滑动窗口引擎及4尺度TTA，带来+10.57%的性能提升。GOOSE-M2F达到70.08%官方综合mIoU（细粒度63.55%，粗粒度76.61%），在GOOSE 2D FGSS排行榜上位列第三。代码与预训练模型已开源：\href{https://github.com/Aditya-Lingam-9000/GOOSE-M2F}{GitHub GOOSE-M2F代码}及\href{https://huggingface.co/XYZ9843/GOOSE-M2F}{Hugging Face GOOSE-M2F}。