# Object Detection on NS-FB (balanced) Source: [Object Detection on NS-FB (balanced)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:22:38.248Z Evaluation of Object Detection performance on the balanced split of the NS-FB dataset, reporting standard COCO metrics like AP, AP50, AP75, and AR. 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) | NS-FB (balanced) | | Metric | AP | | 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 - [AP](): Higher is better; unit: PERCENT. - [AP@50](): Higher is better; unit: PERCENT. - [AP@75](): Higher is better; unit: PERCENT. - [AR](): Higher is better; unit: PERCENT. - [AR (Small)](): Higher is better; unit: PERCENT. - [AR (Medium)](): Higher is better; unit: PERCENT. - [AR (Large)](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP | Result date | Report paper | | --- | --- | --- | --- | | RRPN + ResNet-101 | 35.5 | Not recorded | 68fa66591e209131cea0faeb | | RRPN + ResNeXt-101 | 35.4 | Not recorded | 68fa66591e209131cea0faeb | | Selective Search + ResNet-101 | 33.6 | Not recorded | 68fa66591e209131cea0faeb | | Selective Search + ResNeXt-101 | 33.2 | Not recorded | 68fa66591e209131cea0faeb | ### RRPN + ResNet-101 AP: 35.5. Result ID: 698ceb4c8b517eb4331dadce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Proposal Method":"RRPN","Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### RRPN + ResNeXt-101 AP: 35.4. Result ID: 698ceb4c8b517eb4331dadcd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Proposal Method":"RRPN","Backbone":"ResNeXt-101"}. This record does not assert independent reproduction. ### Selective Search + ResNet-101 AP: 33.6. Result ID: 698ceb4c8b517eb4331dadcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Proposal Method":"Selective Search","Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### Selective Search + ResNeXt-101 AP: 33.2. Result ID: 698ceb4c8b517eb4331dadcb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Proposal Method":"Selective Search","Backbone":"ResNeXt-101"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.