# Infrastructure Improvement Proposal on Mapillary (test) Source: [Infrastructure Improvement Proposal on Mapillary (test)]() Collection index: [llms.txt]() Data updated: 2026-03-09T07:51:26.308Z Evaluation of model performance on generating or assessing infrastructure improvement proposals using the test split of the Mapillary dataset, reporting standard classification 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 | infrastructure improvement proposal | | Dataset (including any stated split) | Mapillary (test) | | Metric | Recall | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Recall](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [F1-Score](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Recall | Result date | Report paper | | --- | --- | --- | --- | | Qwen2-VL | 84.42 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 77.77 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 77.1 | Not recorded | 69ae53da2d603e6de3e4281a | | LLaVA-1.5 | 75.74 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 75.63 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 74.76 | Not recorded | 69ae53da2d603e6de3e4281a | | InternVL2 | 72.36 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (ResNet-50) | 65.49 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (ViT-B) | 63.65 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (CLIP) | 63.09 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (Long-CLIP) | 62.34 | Not recorded | 69ae53da2d603e6de3e4281a | | GPT-4o | 61.04 | Not recorded | 69ae53da2d603e6de3e4281a | | GPT-4o | 51.87 | Not recorded | 69ae53da2d603e6de3e4281a | | Phi-3 | 51.35 | Not recorded | 69ae53da2d603e6de3e4281a | | LLaVA-1.5 | 42.17 | Not recorded | 69ae53da2d603e6de3e4281a | | Phi-3 | 41.27 | Not recorded | 69ae53da2d603e6de3e4281a | | Qwen2-VL | 40.99 | Not recorded | 69ae53da2d603e6de3e4281a | | InternVL2 | 34.57 | Not recorded | 69ae53da2d603e6de3e4281a | ### Qwen2-VL Recall: 84.42. Result ID: 69ae7bee6dbb7075b9565e6f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ours Baseline Recall: 77.77. Result ID: 69ae7bee6dbb7075b9565e6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"ViT-B","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### Ours Baseline Recall: 77.1. Result ID: 69ae7bee6dbb7075b9565e6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"Long-CLIP","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### LLaVA-1.5 Recall: 75.74. Result ID: 69ae7bee6dbb7075b9565e6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ours Baseline Recall: 75.63. Result ID: 69ae7bee6dbb7075b9565e6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"CLIP","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### Ours Baseline Recall: 74.76. Result ID: 69ae7bee6dbb7075b9565e69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"ResNet-50","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### InternVL2 Recall: 72.36. Result ID: 69ae7bee6dbb7075b9565e71. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OD-RASE (ResNet-50) Recall: 65.49. Result ID: 69ae7bee6dbb7075b9565e57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"ResNet-50","Text Encoder":"RoBERTa-Base","Evaluation Setting":"zero-shot","Training Dataset":"BDD100K"}. This record does not assert independent reproduction. ### OD-RASE (ViT-B) Recall: 63.65. Result ID: 69ae7bee6dbb7075b9565e58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"ViT-B","Text Encoder":"RoBERTa-Base","Evaluation Setting":"zero-shot","Training Dataset":"BDD100K"}. This record does not assert independent reproduction. ### OD-RASE (CLIP) Recall: 63.09. Result ID: 69ae7bee6dbb7075b9565e59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"CLIP","Text Encoder":"RoBERTa-Base","Evaluation Setting":"zero-shot","Training Dataset":"BDD100K"}. This record does not assert independent reproduction. ### OD-RASE (Long-CLIP) Recall: 62.34. Result ID: 69ae7bee6dbb7075b9565e5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"Long-CLIP","Text Encoder":"RoBERTa-Base","Evaluation Setting":"zero-shot","Training Dataset":"BDD100K"}. This record does not assert independent reproduction. ### GPT-4o Recall: 61.04. Result ID: 69ae7bee6dbb7075b9565e5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### GPT-4o Recall: 51.87. Result ID: 69ae7bee6dbb7075b9565e6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Phi-3 Recall: 51.35. Result ID: 69ae7bee6dbb7075b9565e70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaVA-1.5 Recall: 42.17. Result ID: 69ae7bee6dbb7075b9565e5c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### Phi-3 Recall: 41.27. Result ID: 69ae7bee6dbb7075b9565e5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### Qwen2-VL Recall: 40.99. Result ID: 69ae7bee6dbb7075b9565e5d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### InternVL2 Recall: 34.57. Result ID: 69ae7bee6dbb7075b9565e5f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.