# Camouflaged Object Detection on OVCOD-D 1.0 (union of base and novel classes)

Source: [Camouflaged Object Detection on OVCOD-D 1.0 (union of base and novel classes)](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes>)

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

Data updated: 2026-03-30T07:10:36.040Z

Evaluation of Camouflaged Object Detection performance on the OVCOD-D 1.0 dataset, which includes a union of base and novel classes, reporting standard object detection metrics (AP family).

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 | Camouflaged Object Detection |
| Dataset (including any stated split) | OVCOD-D 1.0 (union of base and novel classes) |
| Metric | AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes.md?metric=AP>): Higher is better; unit: PERCENT.

- [AP50](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes.md?metric=AP50>): Higher is better; unit: PERCENT.

- [AP75](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes.md?metric=AP75>): Higher is better; unit: PERCENT.

- [APm](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes.md?metric=APm>): Higher is better; unit: PERCENT.

- [APl](<https://www.sota2.com/research/sota/camouflaged-object-detection-on-ovcod-d-1-0-union-of-base-and-novel-classes.md?metric=APl>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| SDDF-L | 56.4 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| SDDF-M | 54.3 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| DOSOD-L | 53.4 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| DOSOD-M | 51.8 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| SDDF-S | 48.1 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| YOLO-World-L | 45.7 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| DOSOD-S | 44.8 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| YOLO-World-M | 43.3 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| YOLOE-M | 39.9 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| YOLOE-S | 38.7 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| YOLO-World-S | 38.5 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| Grounding DINO-T | 34.8 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| GLIPv2-T | 25.6 | Not recorded | 69ca035b0636e5bf4afc91c2 |
| GLIP-T | 22.6 | Not recorded | 69ca035b0636e5bf4afc91c2 |

### SDDF-L

AP: 56.4. Result ID: 69ca21dd47f34ce924b24f7e.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-L","Params":"109M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### SDDF-M

AP: 54.3. Result ID: 69ca21dd47f34ce924b24f7d.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-M","Params":"91M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### DOSOD-L

AP: 53.4. Result ID: 69ca21dd47f34ce924b24f7b.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76591e209131cea6c85a.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-L","Params":"108M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### DOSOD-M

AP: 51.8. Result ID: 69ca21dd47f34ce924b24f7a.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76591e209131cea6c85a.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-M","Params":"90M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### SDDF-S

AP: 48.1. Result ID: 69ca21dd47f34ce924b24f7c.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-S","Params":"76M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### YOLO-World-L

AP: 45.7. Result ID: 69ca21dd47f34ce924b24f76.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-L","Params":"110M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### DOSOD-S

AP: 44.8. Result ID: 69ca21dd47f34ce924b24f79.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76591e209131cea6c85a.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-S","Params":"75M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### YOLO-World-M

AP: 43.3. Result ID: 69ca21dd47f34ce924b24f75.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-M","Params":"92M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### YOLOE-M

AP: 39.9. Result ID: 69ca21dd47f34ce924b24f78.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c3c1e209131cea8d10c.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-M","Params":"94M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### YOLOE-S

AP: 38.7. Result ID: 69ca21dd47f34ce924b24f77.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c3c1e209131cea8d10c.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-S","Params":"78M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### YOLO-World-S

AP: 38.5. Result ID: 69ca21dd47f34ce924b24f74.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv8-S","Params":"77M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### Grounding DINO-T

AP: 34.8. Result ID: 69ca21dd47f34ce924b24f73.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

Recorded evaluation configuration: {"Backbone":"Swin-T","Params":"172M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### GLIPv2-T

AP: 25.6. Result ID: 69ca21dd47f34ce924b24f72.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9d1e209131cea3ad6c.md>)

Recorded evaluation configuration: {"Backbone":"Swin-T","Params":"232M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

### GLIP-T

AP: 22.6. Result ID: 69ca21dd47f34ce924b24f71.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035b0636e5bf4afc91c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd91e209131cea36418.md>)

[Implementation](<https://github.com/microsoft/GLIP>)

Recorded evaluation configuration: {"Backbone":"Swin-T","Params":"232M","Pre-train":"O365,GoldG"}. This record does not assert independent reproduction.

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