# 3D Object Detection on nuScenes (val) (Specific Threshold Metrics) Source: [3D Object Detection on nuScenes (val) (Specific Threshold Metrics)]() Collection index: [llms.txt]() Data updated: 2026-03-11T08:45:50.178Z Evaluation of 3D Object Detection performance on the nuScenes validation set, focusing on overall scores (mAP (All), NDS (All)) and scores related to a specific condition or distance threshold (1). 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 | 3D Object Detection | | Dataset (including any stated split) | nuScenes (val) | | Metric | mAP (Threshold 1) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [mAP (Threshold 1)](): Higher is better; unit: PERCENT. - [mAP (All)](): Higher is better; unit: PERCENT. - [NDS (Threshold 1)](): Higher is better; unit: PERCENT. - [NDS (All)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mAP (Threshold 1) | Result date | Report paper | | --- | --- | --- | --- | | Joint Training | 59.6 | Not recorded | 69b0f7292d603e6de3e45f31 | | CL-DETR | 53.5 | Not recorded | 69b0f7292d603e6de3e45f31 | | OMEN | 52.3 | Not recorded | 69b0f7292d603e6de3e45f31 | | Pseudo-Labeling | 49.9 | Not recorded | 69b0f7292d603e6de3e45f31 | | Pseudo-Labeling | 45.9 | Not recorded | 69b0f7292d603e6de3e45f31 | | Forgetting | 0 | Not recorded | 69b0f7292d603e6de3e45f31 | ### Joint Training mAP (Threshold 1): 59.6. Result ID: 69b12bb96dbb7075b95ba883. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CL-DETR mAP (Threshold 1): 53.5. Result ID: 69b12bb96dbb7075b95ba887. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"future pseudo-labeling":"true"}. This record does not assert independent reproduction. ### OMEN mAP (Threshold 1): 52.3. Result ID: 69b12bb96dbb7075b95ba888. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"per-class incremental setting":"true"}. This record does not assert independent reproduction. ### Pseudo-Labeling mAP (Threshold 1): 49.9. Result ID: 69b12bb96dbb7075b95ba886. [Reporting paper]() Recorded evaluation configuration: {"future pseudo-labeling":"true"}. This record does not assert independent reproduction. ### Pseudo-Labeling mAP (Threshold 1): 45.9. Result ID: 69b12bb96dbb7075b95ba885. [Reporting paper]() Recorded evaluation configuration: {"future pseudo-labeling":"false"}. This record does not assert independent reproduction. ### Forgetting mAP (Threshold 1): 0. Result ID: 69b12bb96dbb7075b95ba884. [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.