# Simultaneous Detection and Segmentation on VOC 2012 (val) Source: [Simultaneous Detection and Segmentation on VOC 2012 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:30.372Z Evaluation of Instance Segmentation performance on the validation split of the PASCAL VOC 2012 dataset, reporting per-class AP^r scores. 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 | Simultaneous Detection and Segmentation | | Dataset (including any stated split) | VOC 2012 (val) | | Metric | AP^r (aeroplane) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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^r (aeroplane)](): Higher is better; unit: PERCENT. - [AP^r (bicycle)](): Higher is better; unit: PERCENT. - [AP^r (bird)](): Higher is better; unit: PERCENT. - [AP^r (boat)](): Higher is better; unit: PERCENT. - [AP^r (bottle)](): Higher is better; unit: PERCENT. - [AP^r (bus)](): Higher is better; unit: PERCENT. - [AP^r (car)](): Higher is better; unit: PERCENT. - [AP^r (cat)](): Higher is better; unit: PERCENT. - [AP^r (chair)](): Higher is better; unit: PERCENT. - [AP^r (cow)](): Higher is better; unit: PERCENT. - [AP^r (diningtable)](): Higher is better; unit: PERCENT. - [AP^r (dog)](): Higher is better; unit: PERCENT. - [AP^r (horse)](): Higher is better; unit: PERCENT. - [AP^r (motorbike)](): Higher is better; unit: PERCENT. - [AP^r (person)](): Higher is better; unit: PERCENT. - [AP^r (pottedplant)](): Higher is better; unit: PERCENT. - [AP^r (sheep)](): Higher is better; unit: PERCENT. - [AP^r (sofa)](): Higher is better; unit: PERCENT. - [AP^r (train)](): Higher is better; unit: PERCENT. - [AP^r (tvmonitor)](): Higher is better; unit: PERCENT. - [Mean AP^r](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP^r (aeroplane) | Result date | Report paper | | --- | --- | --- | --- | | SDS (C+ref) | 68.4 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS (C) | 67.4 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS (B) | 65.7 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS (A) | 61.8 | Not recorded | 68fa616a1e209131ce9f4432 | | O2P | 56.5 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS | 53.2 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS | 52.3 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS | 51.1 | Not recorded | 68fa616a1e209131ce9f4432 | | SDS | 48.3 | Not recorded | 68fa616a1e209131ce9f4432 | | O2P | 46.8 | Not recorded | 68fa616a1e209131ce9f4432 | ### SDS (C+ref) AP^r (aeroplane): 68.4. Result ID: 698bcca67a967eddb77171ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"features":"CNN features on boxes and regions","refinement":"true"}. This record does not assert independent reproduction. ### SDS (C) AP^r (aeroplane): 67.4. Result ID: 698bcca67a967eddb77171ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"features":"CNN features on boxes and regions"}. This record does not assert independent reproduction. ### SDS (B) AP^r (aeroplane): 65.7. Result ID: 698bcca67a967eddb77171ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"features":"CNN features on regions"}. This record does not assert independent reproduction. ### SDS (A) AP^r (aeroplane): 61.8. Result ID: 698bcca67a967eddb77171eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"features":"CNN features on boxes"}. This record does not assert independent reproduction. ### O2P AP^r (aeroplane): 56.5. Result ID: 698bcca67a967eddb77171ea. [Reporting paper]() Recorded evaluation configuration: {"features":"Second-order pooling"}. This record does not assert independent reproduction. ### SDS AP^r (aeroplane): 53.2. Result ID: 698c660037894ef7d9ce16eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Configuration":"C"}. This record does not assert independent reproduction. ### SDS AP^r (aeroplane): 52.3. Result ID: 698c660037894ef7d9ce16ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Configuration":"C+ref"}. This record does not assert independent reproduction. ### SDS AP^r (aeroplane): 51.1. Result ID: 698c660037894ef7d9ce16ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Configuration":"B"}. This record does not assert independent reproduction. ### SDS AP^r (aeroplane): 48.3. Result ID: 698c660037894ef7d9ce16e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Configuration":"A"}. This record does not assert independent reproduction. ### O2P AP^r (aeroplane): 46.8. Result ID: 698c660037894ef7d9ce16e8. [Reporting paper]() Recorded evaluation configuration: {"Configuration":"O2P"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.