# Object Detection on VisDA COCO17 2018 (val)

Source: [Object Detection on VisDA COCO17 2018 (val)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:23:10.798Z

Evaluation of Object Detection performance on the VisDA COCO 2017 dataset validation split from 2018, reporting per-class detection scores and overall mAP.

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) | VisDA COCO17 2018 (val) |
| Metric | AP (plane) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 (plane)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(plane)>): Higher is better; unit: PERCENT.

- [AP (bcycl)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(bcycl)>): Higher is better; unit: PERCENT.

- [AP (bus)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(bus)>): Higher is better; unit: PERCENT.

- [AP (car)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(car)>): Higher is better; unit: PERCENT.

- [AP (horse)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(horse)>): Higher is better; unit: PERCENT.

- [AP (knife)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(knife)>): Higher is better; unit: PERCENT.

- [AP (mcycl)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(mcycl)>): Higher is better; unit: PERCENT.

- [AP (person)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(person)>): Higher is better; unit: PERCENT.

- [AP (plant)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(plant)>): Higher is better; unit: PERCENT.

- [AP (sktbrd)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(sktbrd)>): Higher is better; unit: PERCENT.

- [AP (train)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(train)>): Higher is better; unit: PERCENT.

- [AP (truck)](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=AP%20(truck)>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/object-detection-on-visda-coco17-2018-val.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP (plane) | Result date | Report paper |
| --- | --- | --- | --- |
| SWD | 11.9 | Not recorded | 68fa656e1e209131cea0a56d |
| MCD | 11.8 | Not recorded | 68fa656e1e209131cea0a56d |
| Source only | 0.5 | Not recorded | 68fa656e1e209131cea0a56d |

### SWD

AP (plane): 11.9. Result ID: 698cac198b517eb4331bf443.

[Reporting paper](<https://www.sota2.com/research/paper/68fa656e1e209131cea0a56d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa656e1e209131cea0a56d.md>)

Recorded evaluation configuration: {"Backbone":"Inception-V2","Detector Architecture":"SSD","IoU Threshold":"0.5"}. This record does not assert independent reproduction.

### MCD

AP (plane): 11.8. Result ID: 698cac198b517eb4331bf442.

[Reporting paper](<https://www.sota2.com/research/paper/68fa656e1e209131cea0a56d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea03641.md>)

[Implementation](<https://github.com/mil-tokyo/MCD_DA>)

Recorded evaluation configuration: {"Backbone":"Inception-V2","Detector Architecture":"SSD","IoU Threshold":"0.5"}. This record does not assert independent reproduction.

### Source only

AP (plane): 0.5. Result ID: 698cac198b517eb4331bf441.

[Reporting paper](<https://www.sota2.com/research/paper/68fa656e1e209131cea0a56d.md>)

Recorded evaluation configuration: {"Backbone":"Inception-V2","Detector Architecture":"SSD","IoU Threshold":"0.5"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.