# Reasoning Segmentation on SegEarth-R2 (train) Source: [Reasoning Segmentation on SegEarth-R2 (train)]() Collection index: [llms.txt]() Data updated: 2026-03-05T09:11:09.393Z Evaluation of Reasoning Segmentation performance on the training split of the SegEarth-R2 dataset, reporting standard segmentation metrics like IoU, Dice, Accuracy, Precision, Recall, Specificity, and BF. 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 | Reasoning Segmentation | | Dataset (including any stated split) | SegEarth-R2 (train) | | Metric | Mean IoU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Mean IoU](): Higher is better; unit: PERCENT. - [Dice Coefficient](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Specificity](): Higher is better; unit: PERCENT. - [Boundary F-score (BF)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Mean IoU | Result date | Report paper | | --- | --- | --- | --- | | LISA-7B | 26 | Not recorded | 69a90e162d603e6de3e408ee | | GeoSeg | 17.4 | Not recorded | 69a90e162d603e6de3e408ee | | CLIP Surgery + SAM3 | 14.5 | Not recorded | 69a90e162d603e6de3e408ee | | Grounded SAM | 11.3 | Not recorded | 69a90e162d603e6de3e408ee | | SAM3 | 10.5 | Not recorded | 69a90e162d603e6de3e408ee | | BAGEL | 8.8 | Not recorded | 69a90e162d603e6de3e408ee | | GSVA | 7.5 | Not recorded | 69a90e162d603e6de3e408ee | | UniWorld | 6.4 | Not recorded | 69a90e162d603e6de3e408ee | | Qwen-Edit | 5.8 | Not recorded | 69a90e162d603e6de3e408ee | | OmniGen2 | 5.8 | Not recorded | 69a90e162d603e6de3e408ee | | Hunyuan | 4.3 | Not recorded | 69a90e162d603e6de3e408ee | | LISA++ | 3.7 | Not recorded | 69a90e162d603e6de3e408ee | | PixelLM | 2.4 | Not recorded | 69a90e162d603e6de3e408ee | | GLAMM | 0 | Not recorded | 69a90e162d603e6de3e408ee | ### LISA-7B Mean IoU: 26. Result ID: 69a948966dbb7075b952f7d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Reasoning segmentation"}. This record does not assert independent reproduction. ### GeoSeg Mean IoU: 17.4. Result ID: 69a948966dbb7075b952f7da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Ours"}. This record does not assert independent reproduction. ### CLIP Surgery + SAM3 Mean IoU: 14.5. Result ID: 69a948966dbb7075b952f7cf. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Generalist segmentation"}. This record does not assert independent reproduction. ### Grounded SAM Mean IoU: 11.3. Result ID: 69a948966dbb7075b952f7ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Generalist segmentation"}. This record does not assert independent reproduction. ### SAM3 Mean IoU: 10.5. Result ID: 69a948966dbb7075b952f7cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Generalist segmentation"}. This record does not assert independent reproduction. ### BAGEL Mean IoU: 8.8. Result ID: 69a948966dbb7075b952f7d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Open-source MLLMs"}. This record does not assert independent reproduction. ### GSVA Mean IoU: 7.5. Result ID: 69a948966dbb7075b952f7d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Reasoning segmentation"}. This record does not assert independent reproduction. ### UniWorld Mean IoU: 6.4. Result ID: 69a948966dbb7075b952f7d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Open-source MLLMs"}. This record does not assert independent reproduction. ### Qwen-Edit Mean IoU: 5.8. Result ID: 69a948966dbb7075b952f7d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Open-source MLLMs"}. This record does not assert independent reproduction. ### OmniGen2 Mean IoU: 5.8. Result ID: 69a948966dbb7075b952f7d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Open-source MLLMs"}. This record does not assert independent reproduction. ### Hunyuan Mean IoU: 4.3. Result ID: 69a948966dbb7075b952f7d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Open-source MLLMs"}. This record does not assert independent reproduction. ### LISA++ Mean IoU: 3.7. Result ID: 69a948966dbb7075b952f7d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Reasoning segmentation"}. This record does not assert independent reproduction. ### PixelLM Mean IoU: 2.4. Result ID: 69a948966dbb7075b952f7d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Reasoning segmentation"}. This record does not assert independent reproduction. ### GLAMM Mean IoU: 0. Result ID: 69a948966dbb7075b952f7d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Reasoning segmentation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.