# Scene Graph Classification on VG 1800 (test) Source: [Scene Graph Classification on VG 1800 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:59.222Z Evaluation of Scene Graph Classification performance on the test split of the VG 1800 dataset, measured using Top-K Accuracy metrics. 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 | Scene Graph Classification | | Dataset (including any stated split) | VG 1800 (test) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Top-1 Mean Accuracy (mAcc)](): Higher is better; unit: PERCENT. - [Top-1 F-Accuracy (F-Acc)](): Higher is better; unit: PERCENT. - [Top-1 Non-Zero Count](): Higher is better; unit: SCALAR. - [Top-5 Accuracy](): Higher is better; unit: PERCENT. - [Top-5 Mean Accuracy (mAcc)](): Higher is better; unit: PERCENT. - [Top-5 F-Accuracy (F-Acc)](): Higher is better; unit: SCALAR. - [Top-5 Non-Zero Count](): Higher is better; unit: SCALAR. - [Top-10 Accuracy](): Higher is better; unit: PERCENT. - [Top-10 Mean Accuracy (mAcc)](): Higher is better; unit: SCALAR. - [Top-10 F-Accuracy (F-Acc)](): Higher is better; unit: SCALAR. - [Top-10 Non-Zero Count](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Motif | 0.1893 | Not recorded | 68fa6d181e209131cea37ae8 | | Motif + Focal Loss | 0.1855 | Not recorded | 68fa6d181e209131cea37ae8 | | Motif + RelMix | 0.1827 | Not recorded | 68fa6d181e209131cea37ae8 | | Motif + IETrans | 0.1824 | Not recorded | 68fa6d181e209131cea37ae8 | | Motif + TDE | 0.1802 | Not recorded | 68fa6d181e209131cea37ae8 | | BGNN | 0.1629 | Not recorded | 68fa6d181e209131cea37ae8 | | Motif + IETrans | 0.0491 | Not recorded | 68fa6d181e209131cea37ae8 | ### Motif Top-1 Accuracy: 0.1893. Result ID: 698f8d763a6c314849fa0b52. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Motif"}. This record does not assert independent reproduction. ### Motif + Focal Loss Top-1 Accuracy: 0.1855. Result ID: 698f8d763a6c314849fa0b53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Motif","Loss Function":"Focal Loss"}. This record does not assert independent reproduction. ### Motif + RelMix Top-1 Accuracy: 0.1827. Result ID: 698f8d763a6c314849fa0b55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Motif","Augmentation Strategy":"RelMix"}. This record does not assert independent reproduction. ### Motif + IETrans Top-1 Accuracy: 0.1824. Result ID: 698f8d763a6c314849fa0b56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Motif","Transfer Ratio (kt)":"10%"}. This record does not assert independent reproduction. ### Motif + TDE Top-1 Accuracy: 0.1802. Result ID: 698f8d763a6c314849fa0b54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Motif","Debiasing Strategy":"TDE"}. This record does not assert independent reproduction. ### BGNN Top-1 Accuracy: 0.1629. Result ID: 698f8d763a6c314849fa0b51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"BGNN"}. This record does not assert independent reproduction. ### Motif + IETrans Top-1 Accuracy: 0.0491. Result ID: 698f8d763a6c314849fa0b57. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Motif","Transfer Ratio (kt)":"90%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.