# Visual Grounding on RefCOCOg (test-u) Source: [Visual Grounding on RefCOCOg (test-u)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:56.186Z Evaluation of Visual Grounding performance on the test-unseen split (test-u) of the RefCOCOg dataset. 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 | Visual Grounding | | Dataset (including any stated split) | RefCOCOg (test-u) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 20 of 20 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Accuracy @ 0.5](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ONE-PEACE | 89.27 | Not recorded | 68fa6f6f1e209131cea45899 | | OFA | 88.78 | Not recorded | 68fa6f6f1e209131cea45899 | | FIBER | 87.32 | Not recorded | 68fa6f6f1e209131cea45899 | | Grounding-DINO | 87.02 | Not recorded | 68fa6f6f1e209131cea45899 | | UNICORN | 83.93 | Not recorded | 68fa6f6f1e209131cea45899 | | SeqTR | 83.37 | Not recorded | 68fa6e0c1e209131cea3dad7 | | MDETR | 80.89 | Not recorded | 68fa6e0c1e209131cea3dad7 | | MDETR | 80.89 | Not recorded | 68fa6f6f1e209131cea45899 | | RefTR | 80.01 | Not recorded | 68fa6e0c1e209131cea3dad7 | | VILLA\_L | 76.71 | Not recorded | 68fa6e0c1e209131cea3dad7 | | VILLA | 76.71 | Not recorded | 68fa6f6f1e209131cea45899 | | UNITER\_L | 75.77 | Not recorded | 68fa6e0c1e209131cea3dad7 | | UNITER | 75.77 | Not recorded | 68fa6f6f1e209131cea45899 | | VL-T5 | 71.3 | Not recorded | 68fa6f6f1e209131cea45899 | ### ONE-PEACE Accuracy: 89.27. Result ID: 6990d0853a6c314849037d68. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OFA Accuracy: 88.78. Result ID: 6990d0853a6c314849037d67. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FIBER Accuracy: 87.32. Result ID: 6990d0853a6c314849037d66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Grounding-DINO Accuracy: 87.02. Result ID: 6990d0853a6c314849037d65. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UNICORN Accuracy: 83.93. Result ID: 6990d0853a6c314849037d64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SeqTR Accuracy: 83.37. Result ID: 698ff6f13a6c314849fd20d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Encoder":"DN53","Params (M)":"7.90","Pre-train images":"174K"}. This record does not assert independent reproduction. ### MDETR Accuracy: 80.89. Result ID: 698ff6f13a6c314849fd20d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Encoder":"RN101","Params (M)":"17.36","Pre-train images":"200K"}. This record does not assert independent reproduction. ### MDETR Accuracy: 80.89. Result ID: 6990d0853a6c314849037d63. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RefTR Accuracy: 80.01. Result ID: 698ff6f13a6c314849fd20d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Visual Encoder":"RN101","Params (M)":"17.86","Pre-train images":"100K"}. This record does not assert independent reproduction. ### VILLA\_L Accuracy: 76.71. Result ID: 698ff6f13a6c314849fd20d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Encoder":"RN101","Params (M)":"4.6","Pre-train images":"4.0M"}. This record does not assert independent reproduction. ### VILLA Accuracy: 76.71. Result ID: 6990d0853a6c314849037d62. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UNITER\_L Accuracy: 75.77. Result ID: 698ff6f13a6c314849fd20d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Visual Encoder":"RN101","Params (M)":"4.6","Pre-train images":"4.0M"}. This record does not assert independent reproduction. ### UNITER Accuracy: 75.77. Result ID: 6990d0853a6c314849037d61. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VL-T5 Accuracy: 71.3. Result ID: 6990d0853a6c314849037d60. [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.