# Object Detection on COCO-based Synthetic Images

Source: [Object Detection on COCO-based Synthetic Images](<https://www.sota2.com/research/sota/object-detection-on-coco-based-synthetic-images>)

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

Data updated: 2026-02-26T05:40:45.643Z

Evaluation of Object Detection performance on synthetic images derived from the COCO dataset, focusing on operational metrics such as processing time, cost, and failure analysis, rather than standard accuracy metrics.

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) | COCO-based Synthetic Images |
| Metric | Detected Objects Count |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Detected Objects Count](<https://www.sota2.com/research/sota/object-detection-on-coco-based-synthetic-images.md?metric=Detected%20Objects%20Count>): Higher is better; unit: SCALAR.

- [Detection Failure Rate](<https://www.sota2.com/research/sota/object-detection-on-coco-based-synthetic-images.md?metric=Detection%20Failure%20Rate>): Lower is better; unit: PERCENT.

- [Processing Time (Hours)](<https://www.sota2.com/research/sota/object-detection-on-coco-based-synthetic-images.md?metric=Processing%20Time%20(Hours)>): Lower is better; unit: TIME.

- [Total Cost (USD)](<https://www.sota2.com/research/sota/object-detection-on-coco-based-synthetic-images.md?metric=Total%20Cost%20(USD)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Detected Objects Count | Result date | Report paper |
| --- | --- | --- | --- |
| RCNN Inception | 7349 | Not recorded | 68fa66d11e209131cea1298b |
| RCNN Resnet | 6914 | Not recorded | 68fa66d11e209131cea1298b |
| Amazon Rekognition API | 3750 | Not recorded | 68fa66d11e209131cea1298b |
| SSD Inception | 2806 | Not recorded | 68fa66d11e209131cea1298b |
| SSD Mobilenet | 2387 | Not recorded | 68fa66d11e209131cea1298b |
| Microsoft Azure Vision API | 1985 | Not recorded | 68fa66d11e209131cea1298b |
| Google AutoML Vision API | 1801 | Not recorded | 68fa66d11e209131cea1298b |
| IBM Vision API | 1290 | Not recorded | 68fa66d11e209131cea1298b |

### RCNN Inception

Detected Objects Count: 7349. Result ID: 698d0a1e8b517eb4331e8b26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62331e209131ce9f8333.md>)

Recorded evaluation configuration: {"#Synthetic Images":"76,257"}. This record does not assert independent reproduction.

### RCNN Resnet

Detected Objects Count: 6914. Result ID: 698d0a1e8b517eb4331e8b25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79f3.md>)

[Implementation](<https://github.com/rbgirshick/fast-rcnn>)

Recorded evaluation configuration: {"#Synthetic Images":"70,754"}. This record does not assert independent reproduction.

### Amazon Rekognition API

Detected Objects Count: 3750. Result ID: 698d0a1e8b517eb4331e8b1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

Recorded evaluation configuration: {"#Synthetic Images":"38,939"}. This record does not assert independent reproduction.

### SSD Inception

Detected Objects Count: 2806. Result ID: 698d0a1e8b517eb4331e8b24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63091e209131ce9fc889.md>)

[Implementation](<https://github.com/weiliu89/caffe/tree/ssd>)

Recorded evaluation configuration: {"#Synthetic Images":"29,072"}. This record does not assert independent reproduction.

### SSD Mobilenet

Detected Objects Count: 2387. Result ID: 698d0a1e8b517eb4331e8b23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fdf55.md>)

Recorded evaluation configuration: {"#Synthetic Images":"24,796"}. This record does not assert independent reproduction.

### Microsoft Azure Vision API

Detected Objects Count: 1985. Result ID: 698d0a1e8b517eb4331e8b21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

Recorded evaluation configuration: {"#Synthetic Images":"20,453"}. This record does not assert independent reproduction.

### Google AutoML Vision API

Detected Objects Count: 1801. Result ID: 698d0a1e8b517eb4331e8b20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

Recorded evaluation configuration: {"#Synthetic Images":"18,655"}. This record does not assert independent reproduction.

### IBM Vision API

Detected Objects Count: 1290. Result ID: 698d0a1e8b517eb4331e8b22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66d11e209131cea1298b.md>)

Recorded evaluation configuration: {"#Synthetic Images":"13,280"}. This record does not assert independent reproduction.

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