# Infrastructure Improvement Proposal on Mapillary (val) Source: [Infrastructure Improvement Proposal on Mapillary (val)]() Collection index: [llms.txt]() Data updated: 2026-03-09T07:51:26.274Z Evaluation of performance for identifying and proposing infrastructure improvements using the validation split of the Mapillary dataset, measured using standard classification/prediction metrics like Recall, Precision, F1-Score, and Accuracy. 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 (val) | | 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 | 83.42 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 76.84 | Not recorded | 69ae53da2d603e6de3e4281a | | LLaVA-1.5 | 75.52 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 75.49 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 74.75 | Not recorded | 69ae53da2d603e6de3e4281a | | Ours Baseline | 71.68 | Not recorded | 69ae53da2d603e6de3e4281a | | InternVL2 | 68.27 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (ResNet-50) | 64.38 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (Long-CLIP) | 62.68 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (ViT-B) | 62.49 | Not recorded | 69ae53da2d603e6de3e4281a | | OD-RASE (CLIP) | 60.64 | Not recorded | 69ae53da2d603e6de3e4281a | | Phi-3 | 52.15 | Not recorded | 69ae53da2d603e6de3e4281a | | GPT-4o | 47.19 | Not recorded | 69ae53da2d603e6de3e4281a | | GPT-4o | 43.07 | Not recorded | 69ae53da2d603e6de3e4281a | | Phi-3 | 41.7 | Not recorded | 69ae53da2d603e6de3e4281a | | Qwen2-VL | 41.68 | Not recorded | 69ae53da2d603e6de3e4281a | | LLaVA-1.5 | 39.78 | Not recorded | 69ae53da2d603e6de3e4281a | | InternVL2 | 38.23 | Not recorded | 69ae53da2d603e6de3e4281a | ### Qwen2-VL Recall: 83.42. Result ID: 69ae7bee6dbb7075b9565e66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ours Baseline Recall: 76.84. Result ID: 69ae7bee6dbb7075b9565e61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"ViT-B","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### LLaVA-1.5 Recall: 75.52. Result ID: 69ae7bee6dbb7075b9565e65. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ours Baseline Recall: 75.49. Result ID: 69ae7bee6dbb7075b9565e63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Vision Encoder":"Long-CLIP","Text Encoder":"Long-CLIP"}. This record does not assert independent reproduction. ### Ours Baseline Recall: 74.75. Result ID: 69ae7bee6dbb7075b9565e62. [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: 71.68. Result ID: 69ae7bee6dbb7075b9565e60. [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: 68.27. Result ID: 69ae7bee6dbb7075b9565e68. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OD-RASE (ResNet-50) Recall: 64.38. Result ID: 69ae7bee6dbb7075b9565e4e. [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 (Long-CLIP) Recall: 62.68. Result ID: 69ae7bee6dbb7075b9565e51. [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. ### OD-RASE (ViT-B) Recall: 62.49. Result ID: 69ae7bee6dbb7075b9565e4f. [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: 60.64. Result ID: 69ae7bee6dbb7075b9565e50. [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. ### Phi-3 Recall: 52.15. Result ID: 69ae7bee6dbb7075b9565e67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Recall: 47.19. Result ID: 69ae7bee6dbb7075b9565e64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Recall: 43.07. Result ID: 69ae7bee6dbb7075b9565e52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### Phi-3 Recall: 41.7. Result ID: 69ae7bee6dbb7075b9565e55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### Qwen2-VL Recall: 41.68. Result ID: 69ae7bee6dbb7075b9565e54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### LLaVA-1.5 Recall: 39.78. Result ID: 69ae7bee6dbb7075b9565e53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction. ### InternVL2 Recall: 38.23. Result ID: 69ae7bee6dbb7075b9565e56. [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.