AI模型在ICRA 2026 GOOSE 2D分割挑战赛中取得顶尖排名 · 追踪4个来源

报道来源 [4]

1. arXiv cs.CV TIER_1 English(EN) · Xuesong Wang · 2026-06-19 04:00

   SAM3 自蒸馏用于细粒度 GOOSE 2D 语义分割

   arXiv:2606.20130v1 Announce Type: new Abstract: We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our model adapts t…

2. arXiv cs.CV TIER_1 English(EN) · Xuesong Wang · 2026-06-18 11:54

   SAM3 自我蒸馏用于细粒度 GOOSE 2D 语义分割

   We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our model adapts the image encoder of a recent visual foundation m…

3. arXiv cs.CV TIER_1 English(EN) · Sung-Hoon Yoon · 2026-06-17 01:13

   ICRA 2026 GOOSE 2D 精细语义分割挑战技术报告：利用 DINOv3 实现机器人野外场景的鲁棒性户外场景理解

   The GOOSE 2D Fine-Grained Semantic Segmentation Challenge at the ICRA 2026 Workshop on Field Robotics evaluates dense semantic segmentation of off-road imagery over a fine-grained taxonomy of 64 classes and 11 evaluated non-void coarse categories. We present the first-place solut…

4. arXiv cs.CV TIER_1 English(EN) · Jyothiraditya Lingam, Nikhileswara Rao Sulake, Sai Manikanta Eswar Machara · 2026-06-16 04:00

   GOOSE-M2F：为非结构化户外地形的高保真、长尾细粒度语义分割适配Mask2Former

   arXiv:2606.15937v1 Announce Type: new Abstract: 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…