# Multi-target reasoning segmentation on MUSE (val) Source: [Multi-target reasoning segmentation on MUSE (val)]() Collection index: [llms.txt]() Data updated: 2026-05-20T09:48:03.467Z Evaluation of Multi-target Reasoning Segmentation performance on the validation split of the MUSE dataset, reporting gIoU and cIoU metrics categorized by target count (overall, few targets, many targets). 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 | Multi-target reasoning segmentation | | Dataset (including any stated split) | MUSE (val) | | Metric | Overall gIoU | | 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 - [Overall gIoU](): Higher is better; unit: PERCENT. - [Overall cIoU](): Higher is better; unit: PERCENT. - [Few Targets gIoU](): Higher is better; unit: PERCENT. - [Few Targets cIoU](): Higher is better; unit: PERCENT. - [Many Targets gIoU](): Higher is better; unit: PERCENT. - [Many Targets cIoU](): Higher is better; unit: PERCENT. - [F1@0.5](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall gIoU | Result date | Report paper | | --- | --- | --- | --- | | SETCON | 56.9 | Not recorded | 6a0d405cf984739ed6737b99 | | UGround-7B | 52.4 | Not recorded | 68fa7bde1e209131cea8ae56 | | PixelLM-Llama2-13B | 44.8 | Not recorded | 6a0d405cf984739ed6737b99 | | LISA-Llama2-13B | 43.6 | Not recorded | 6a0d405cf984739ed6737b99 | | PixelLM-7B | 42.6 | Not recorded | 68fa7bde1e209131cea8ae56 | | PixelLM-7B | 42.6 | Not recorded | 6a0d405cf984739ed6737b99 | | Visionreasoner | 42.4 | Not recorded | 6a0d405cf984739ed6737b99 | | LISA-7Baug | 42 | Not recorded | 68fa7bde1e209131cea8ae56 | | LISA-7B | 42 | Not recorded | 6a0d405cf984739ed6737b99 | | SAM3 Agent | 27.8 | Not recorded | 6a0d405cf984739ed6737b99 | | LISA-7Brec | 24.5 | Not recorded | 68fa7bde1e209131cea8ae56 | | LISA-7B | 18.8 | Not recorded | 68fa7bde1e209131cea8ae56 | | SEEM | 13.6 | Not recorded | 68fa7bde1e209131cea8ae56 | ### SETCON Overall gIoU: 56.9. Result ID: 6a0d8340fbc373592c060082. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UGround-7B Overall gIoU: 52.4. Result ID: 699a89315698665ec41353db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w/o SAM":true}. This record does not assert independent reproduction. ### PixelLM-Llama2-13B Overall gIoU: 44.8. Result ID: 6a0d8340fbc373592c06007f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama2-13B"}. This record does not assert independent reproduction. ### LISA-Llama2-13B Overall gIoU: 43.6. Result ID: 6a0d8340fbc373592c06007d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama2-13B"}. This record does not assert independent reproduction. ### PixelLM-7B Overall gIoU: 42.6. Result ID: 699a89315698665ec41353da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"w/o SAM":false}. This record does not assert independent reproduction. ### PixelLM-7B Overall gIoU: 42.6. Result ID: 6a0d8340fbc373592c06007e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"7B"}. This record does not assert independent reproduction. ### Visionreasoner Overall gIoU: 42.4. Result ID: 6a0d8340fbc373592c060081. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LISA-7Baug Overall gIoU: 42. Result ID: 699a89315698665ec41353d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"w/o SAM":false}. This record does not assert independent reproduction. ### LISA-7B Overall gIoU: 42. Result ID: 6a0d8340fbc373592c06007c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"7B"}. This record does not assert independent reproduction. ### SAM3 Agent Overall gIoU: 27.8. Result ID: 6a0d8340fbc373592c060080. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LISA-7Brec Overall gIoU: 24.5. Result ID: 699a89315698665ec41353d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"w/o SAM":false}. This record does not assert independent reproduction. ### LISA-7B Overall gIoU: 18.8. Result ID: 699a89315698665ec41353d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"w/o SAM":false}. This record does not assert independent reproduction. ### SEEM Overall gIoU: 13.6. Result ID: 699a89315698665ec41353d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w/o SAM":true}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.