# Part Segmentation on PartImageNet (val) Source: [Part Segmentation on PartImageNet (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:10:31.424Z Evaluation of Part Segmentation performance on the validation split of the PartImageNet dataset, reporting metrics like mIoU and mACC. 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 | Part Segmentation | | Dataset (including any stated split) | PartImageNet (val) | | 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. - [mACC](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU | Result date | Report paper | | --- | --- | --- | --- | | Compositor | 64.64 | Not recorded | 68fa715a1e209131cea50c93 | | MaskFormer | 63.96 | Not recorded | 68fa715a1e209131cea50c93 | | UniLSeg | 63.87 | Not recorded | 68fa75d61e209131cea6a28a | | UniLSeg | 62.46 | Not recorded | 68fa75d61e209131cea6a28a | | SegFormer | 61.97 | Not recorded | 68fa715a1e209131cea50c93 | | SegFormer | 61.97 | Not recorded | 68fa75d61e209131cea6a28a | | MaskFormer-Dual | 61.69 | Not recorded | 68fa715a1e209131cea50c93 | | Compositor | 61.44 | Not recorded | 68fa715a1e209131cea50c93 | | Deeplab v3+ | 60.57 | Not recorded | 68fa715a1e209131cea50c93 | | DeepLabV3+ | 60.57 | Not recorded | 68fa75d61e209131cea6a28a | | MaskFormer | 60.34 | Not recorded | 68fa715a1e209131cea50c93 | | MaskFormer-Dual | 58.02 | Not recorded | 68fa715a1e209131cea50c93 | | SemanticFPN | 56.76 | Not recorded | 68fa75d61e209131cea6a28a | ### Compositor mIoU: 64.64. Result ID: 6991acef3a6c31484909d1f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Swin-T","params":"51M","training strategy":"Models on parts and objects are trained jointly"}. This record does not assert independent reproduction. ### MaskFormer mIoU: 63.96. Result ID: 6991acef3a6c31484909d1f1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Swin-T","params":"92M (46M×2)","training strategy":"Models on parts and objects are trained separately"}. This record does not assert independent reproduction. ### UniLSeg mIoU: 63.87. Result ID: 699402463a6c3148491a4c16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SA-1B training data scale":"100%"}. This record does not assert independent reproduction. ### UniLSeg mIoU: 62.46. Result ID: 699402463a6c3148491a4c15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SA-1B training data scale":"20%"}. This record does not assert independent reproduction. ### SegFormer mIoU: 61.97. Result ID: 6991acef3a6c31484909d1f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"MiT-B2","params":"48M (24M×2)","training strategy":"Models on parts and objects are trained separately"}. This record does not assert independent reproduction. ### SegFormer mIoU: 61.97. Result ID: 699402463a6c3148491a4c14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MaskFormer-Dual mIoU: 61.69. Result ID: 6991acef3a6c31484909d1f2. [Reporting paper]() Recorded evaluation configuration: {"backbone":"Swin-T","params":"51M","training strategy":"Models on parts and objects are trained jointly"}. This record does not assert independent reproduction. ### Compositor mIoU: 61.44. Result ID: 6991acef3a6c31484909d1ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"ResNet-50","params":"50M","training strategy":"Models on parts and objects are trained jointly"}. This record does not assert independent reproduction. ### Deeplab v3+ mIoU: 60.57. Result ID: 6991acef3a6c31484909d1ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"ResNet-50","params":"84M (42M×2)","training strategy":"Models on parts and objects are trained separately"}. This record does not assert independent reproduction. ### DeepLabV3+ mIoU: 60.57. Result ID: 699402463a6c3148491a4c13. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MaskFormer mIoU: 60.34. Result ID: 6991acef3a6c31484909d1ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"ResNet-50","params":"90M (45M×2)","training strategy":"Models on parts and objects are trained separately"}. This record does not assert independent reproduction. ### MaskFormer-Dual mIoU: 58.02. Result ID: 6991acef3a6c31484909d1ee. [Reporting paper]() Recorded evaluation configuration: {"backbone":"ResNet-50","params":"50M","training strategy":"Models on parts and objects are trained jointly"}. This record does not assert independent reproduction. ### SemanticFPN mIoU: 56.76. Result ID: 699402463a6c3148491a4c12. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.