# Disaster Severity Classification on Synthesized Post-Disaster Street-View Images (test) Source: [Disaster Severity Classification on Synthesized Post-Disaster Street-View Images (test)]() Collection index: [llms.txt]() Data updated: 2026-03-24T13:14:50.676Z Evaluation of Disaster Severity Classification performance on the test split of the Synthesized Post-Disaster Street-View Images dataset, reporting Accuracy, F1 score, and class-specific metrics for Mild, Moderate, and Severe damage levels. 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 | Disaster Severity Classification | | Dataset (including any stated split) | Synthesized Post-Disaster Street-View Images (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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. - [F1 Score](): Higher is better; unit: PERCENT. - [Mild Class Metric](): Higher is better; unit: PERCENT. - [Moderate Class Metric](): Higher is better; unit: PERCENT. - [Severe Class Metric](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Ground Truth | 73 | Not recorded | 69c21a660636e5bf4afc465d | | SD1.5 + ControlNet | 72 | Not recorded | 69c21a660636e5bf4afc465d | | SD1.5 + ControlNet + VLM | 43 | Not recorded | 69c21a660636e5bf4afc465d | | Disaster-MoE | 43 | Not recorded | 69c21a660636e5bf4afc465d | | Pix2Pix | 34 | Not recorded | 69c21a660636e5bf4afc465d | ### Ground Truth Accuracy: 73. Result ID: 69c28d5947f34ce924aabffd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SD1.5 + ControlNet Accuracy: 72. Result ID: 69c28d5947f34ce924aabfff. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"SD1.5","Control":"ControlNet"}. This record does not assert independent reproduction. ### SD1.5 + ControlNet + VLM Accuracy: 43. Result ID: 69c28d5947f34ce924aac000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"SD1.5","Control":"ControlNet","Guidance":"VLM"}. This record does not assert independent reproduction. ### Disaster-MoE Accuracy: 43. Result ID: 69c28d5947f34ce924aac001. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"Mixture-of-Experts"}. This record does not assert independent reproduction. ### Pix2Pix Accuracy: 34. Result ID: 69c28d5947f34ce924aabffe. [Reporting paper]() 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.