用多个视觉编码器融合提升户外场景细粒度分割精度，获ICRA2026亚军。
Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding
- 组合DINOv3、SigLIP2等三类编码器，通过验证集交并比加权融合
- 在GOOSE测试集上达75.40%复合mIoU，超越多数单模型方案
- 预训练策略比参数量或解码器设计更影响性能，适合跨平台场景理解
本文报告了针对ICRA 2026 GOOSE 2D细粒度语义分割挑战的解决方案，需从四个相机平台的无结构户外场景中解析出56类细粒度语义。方法采用基础视觉编码器（DINOv3、SigLIP2、InternImage）与Mask2Former解码器结合，训练时使用长周期、指数移动平均、更大裁剪尺寸及多尺度翻转测试增强。三个编码器因预训练目标互补，通过类别级验证集IoU加权组成预训练多样性集成。在官方GOOSE测试集上，提交结果达到75.40%复合mIoU，获挑战赛第二名。研究进一步表明，编码器的预训练方案而非参数量或解码器设计，是本基准下准确率的关键决定因素。
原文摘要 · Abstract (English)
This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor scenes from four camera platforms into 56 fine-grained categories. Our approach pairs foundation vision encoders (including DINOv3, SigLIP2, and InternImage) with a Mask2Former decoder, and trains them with a strong recipe including long training schedules, exponential moving average, a larger crop size, and multi-scale plus flip test-time augmentation. The three encoders, chosen for their complementary pretraining objectives, are combined into a pretraining-diverse ensemble through per-class validation-IoU weighting. Evaluated on the official GOOSE test set, our submission achieves 75.40% composite mIoU and wins the second place of the challenge. Our study further shows that the encoder's pretraining recipe, rather than its parameter count or the decoder design, is the dominant factor for accuracy on this benchmark.
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。