Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.02593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910099346292736 |
|---|---|
| author | Reid, Ethan |
| author_facet | Reid, Ethan |
| contents | We present Moondream Segmentation, a referring image segmentation extension of Moondream 3, a vision-language model. Given an image and a referring expression, the model autoregressively decodes a vector path and iteratively refines the rasterized mask into a final detailed mask. We introduce a reinforcement learning stage that resolves ambiguity in the supervised signal by directly optimizing mask quality. Rollouts from this stage produce coarse-to-ground-truth targets for the refiner. To mitigate evaluation noise from polygon annotations, we release RefCOCO-M, a cleaned RefCOCO validation split with boundary-accurate masks. Moondream Segmentation achieves a cIoU of 80.2% on RefCOCO (val) and 62.6% mIoU on LVIS (val). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02593 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Moondream Segmentation: From Words to Masks Reid, Ethan Computer Vision and Pattern Recognition Artificial Intelligence We present Moondream Segmentation, a referring image segmentation extension of Moondream 3, a vision-language model. Given an image and a referring expression, the model autoregressively decodes a vector path and iteratively refines the rasterized mask into a final detailed mask. We introduce a reinforcement learning stage that resolves ambiguity in the supervised signal by directly optimizing mask quality. Rollouts from this stage produce coarse-to-ground-truth targets for the refiner. To mitigate evaluation noise from polygon annotations, we release RefCOCO-M, a cleaned RefCOCO validation split with boundary-accurate masks. Moondream Segmentation achieves a cIoU of 80.2% on RefCOCO (val) and 62.6% mIoU on LVIS (val). |
| title | Moondream Segmentation: From Words to Masks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.02593 |