# Object Detection on Pascal VOC 2012 (5i 4-Fold CV) Source: [Object Detection on Pascal VOC 2012 (5i 4-Fold CV)]() Collection index: [llms.txt]() Data updated: 2026-03-20T10:13:04.440Z Evaluation of Object Detection performance on Pascal VOC 2012 data using the 4-fold cross-validation scheme derived from the Pascal-5i setup, reporting results based on mIoU per fold. 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 | Object Detection | | Dataset (including any stated split) | Pascal VOC cross-task from Pascal-5i folds 2012 (4-fold cross-validation) | | Metric | mIoU (Fold 0) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [mIoU (Fold 0)](): Higher is better; unit: PERCENT. - [mIoU (Fold 1)](): Higher is better; unit: PERCENT. - [mIoU (Fold 2)](): Higher is better; unit: PERCENT. - [mIoU (Fold 3)](): Higher is better; unit: PERCENT. - [mIoU (Mean)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU (Fold 0) | Result date | Report paper | | --- | --- | --- | --- | | PromptHub | 43.4 | Not recorded | 69bcd4a50636e5bf4afc2b6b | | PromptHub | 41.59 | Not recorded | 69bcd4a50636e5bf4afc2b6b | | Condenser | 41.25 | Not recorded | 69bcd4a50636e5bf4afc2b6b | | Condenser | 38.15 | Not recorded | 69bcd4a50636e5bf4afc2b6b | ### PromptHub mIoU (Fold 0): 43.4. Result ID: 69bd1d9447f34ce924a7cffe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N (number of prompt pairs)":"16","Cross-task evaluation":"trained on segmentation, evaluated on detection","Inference mode":"Zero-shot / No fine-tuning"}. This record does not assert independent reproduction. ### PromptHub mIoU (Fold 0): 41.59. Result ID: 69bd1d9447f34ce924a7cffd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N (number of prompt pairs)":"1","Cross-task evaluation":"trained on segmentation, evaluated on detection","Inference mode":"Zero-shot / No fine-tuning"}. This record does not assert independent reproduction. ### Condenser mIoU (Fold 0): 41.25. Result ID: 69bd1d9447f34ce924a7cffc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N (number of prompt pairs)":"16","Cross-task evaluation":"trained on segmentation, evaluated on detection","Inference mode":"Zero-shot / No fine-tuning"}. This record does not assert independent reproduction. ### Condenser mIoU (Fold 0): 38.15. Result ID: 69bd1d9447f34ce924a7cffb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N (number of prompt pairs)":"1","Cross-task evaluation":"trained on segmentation, evaluated on detection","Inference mode":"Zero-shot / No fine-tuning"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.