# Referring Expression Segmentation on refCOCOg UMD (test) Source: [Referring Expression Segmentation on refCOCOg UMD (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:10:43.096Z Evaluation of Referring Expression Segmentation performance on the test split of the refCOCOg UMD dataset, measured using mIoU. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Referring Expression Segmentation | | Dataset (including any stated split) | refCOCOg UMD (test) | | Metric | mIoU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [mIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU | Result date | Report paper | | --- | --- | --- | --- | | GETok-R1 | 75.2 | Not recorded | 693ba16d6cfd488761a550bc | | GETok-R1-grid | 73.9 | Not recorded | 693ba16d6cfd488761a550bc | | SAM-R1 | 73.1 | Not recorded | 693ba16d6cfd488761a550bc | | Seg-Zero | 72.6 | Not recorded | 693ba16d6cfd488761a550bc | | VisionReasoner | 72.2 | Not recorded | 693ba16d6cfd488761a550bc | | GETok-SFT-grid | 70.9 | Not recorded | 693ba16d6cfd488761a550bc | | GETok-SFT | 70.9 | Not recorded | 693ba16d6cfd488761a550bc | | PixelLM | 70.5 | Not recorded | 693ba16d6cfd488761a550bc | | LISA | 70.5 | Not recorded | 693ba16d6cfd488761a550bc | | Qwen2.5-VL-7B | 69.9 | Not recorded | 693ba16d6cfd488761a550bc | | ReLA | 66 | Not recorded | 693ba16d6cfd488761a550bc | | LAVT | 62.1 | Not recorded | 693ba16d6cfd488761a550bc | | CRIS | 60.4 | Not recorded | 693ba16d6cfd488761a550bc | ### GETok-R1 mIoU: 75.2. Result ID: 69985e195698665ec4bc9f5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Reinforcement Learning"}. This record does not assert independent reproduction. ### GETok-R1-grid mIoU: 73.9. Result ID: 69985e195698665ec4bc9f59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Reinforcement Learning"}. This record does not assert independent reproduction. ### SAM-R1 mIoU: 73.1. Result ID: 69985e195698665ec4bc9f57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Reinforcement Learning"}. This record does not assert independent reproduction. ### Seg-Zero mIoU: 72.6. Result ID: 69985e195698665ec4bc9f56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Reinforcement Learning"}. This record does not assert independent reproduction. ### VisionReasoner mIoU: 72.2. Result ID: 69985e195698665ec4bc9f58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Reinforcement Learning"}. This record does not assert independent reproduction. ### GETok-SFT-grid mIoU: 70.9. Result ID: 69985e195698665ec4bc9f54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### GETok-SFT mIoU: 70.9. Result ID: 69985e195698665ec4bc9f55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### PixelLM mIoU: 70.5. Result ID: 69985e195698665ec4bc9f51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Mask Dec.":true,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### LISA mIoU: 70.5. Result ID: 69985e195698665ec4bc9f52. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Mask Dec.":true,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B mIoU: 69.9. Result ID: 69985e195698665ec4bc9f53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":false,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### ReLA mIoU: 66. Result ID: 69985e195698665ec4bc9f4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Mask Dec.":true,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### LAVT mIoU: 62.1. Result ID: 69985e195698665ec4bc9f4e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Mask Dec.":true,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. ### CRIS mIoU: 60.4. Result ID: 69985e195698665ec4bc9f50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Mask Dec.":true,"Learning Protocol":"Supervised Fine-Tuning"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.