# Image Classification on ImageNet Cross-Dataset Evaluation Suite

Source: [Image Classification on ImageNet Cross-Dataset Evaluation Suite](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite>)

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

Data updated: 2026-05-14T08:51:13.668Z

Evaluation of Image Classification performance measuring generalization from ImageNet (Source) to 10 distinct target domains (including Caltech101, OxfordPets, StanfordCars, Flowers101, Food101, FGVC-Aircraft, SUN397, DTD, EuroSAT, and UCF101).

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 | Image Classification |
| Dataset (including any stated split) | ImageNet Cross-Dataset Evaluation Suite |
| Metric | Source Domain Accuracy (ImageNet) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Source Domain Accuracy (ImageNet)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=Source%20Domain%20Accuracy%20(ImageNet)>): Higher is better; unit: PERCENT.

- [Average Target Domain Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=Average%20Target%20Domain%20Accuracy>): Higher is better; unit: PERCENT.

- [Caltech101 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=Caltech101%20Accuracy>): Higher is better; unit: PERCENT.

- [OxfordPets Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=OxfordPets%20Accuracy>): Higher is better; unit: PERCENT.

- [StanfordCars Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=StanfordCars%20Accuracy>): Higher is better; unit: PERCENT.

- [Flowers101 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=Flowers101%20Accuracy>): Higher is better; unit: PERCENT.

- [Food101 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=Food101%20Accuracy>): Higher is better; unit: PERCENT.

- [FGVC-Aircraft Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=FGVC-Aircraft%20Accuracy>): Higher is better; unit: PERCENT.

- [SUN397 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=SUN397%20Accuracy>): Higher is better; unit: PERCENT.

- [DTD Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=DTD%20Accuracy>): Higher is better; unit: PERCENT.

- [EuroSAT Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=EuroSAT%20Accuracy>): Higher is better; unit: PERCENT.

- [UCF101 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-cross-dataset-evaluation-suite.md?metric=UCF101%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Source Domain Accuracy (ImageNet) | Result date | Report paper |
| --- | --- | --- | --- |
| TAC | 72.77 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| MMRL | 72.03 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| CoOp | 71.51 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| DeAR | 71.5 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| PromptSRC | 71.27 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| MaPLe | 70.72 | Not recorded | 69a66c142d603e6de3e3cdb4 |
| CoOpOp | 70.62 | Not recorded | 6a055740dbc836b87d828e74 |
| RPO | 69.69 | Not recorded | 6a055740dbc836b87d828e74 |
| CLIP-Adapter | 68.64 | Not recorded | 6a055740dbc836b87d828e74 |

### TAC

Source Domain Accuracy (ImageNet): 72.77. Result ID: 69a8307f6dbb7075b94e9ae9.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MMRL

Source Domain Accuracy (ImageNet): 72.03. Result ID: 69a8307f6dbb7075b94e9ae8.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a11e209131cea747a9.md>)

[Implementation](<https://github.com/yunncheng/MMRL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoOp

Source Domain Accuracy (ImageNet): 71.51. Result ID: 69a8307f6dbb7075b94e9ae5.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8b1e209131cea3a814.md>)

[Implementation](<https://github.com/KaiyangZhou/CoOp>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeAR

Source Domain Accuracy (ImageNet): 71.5. Result ID: 69a8307f6dbb7075b94e9aea.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PromptSRC

Source Domain Accuracy (ImageNet): 71.27. Result ID: 69a8307f6dbb7075b94e9ae7.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705e1e209131cea4aa58.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MaPLe

Source Domain Accuracy (ImageNet): 70.72. Result ID: 69a8307f6dbb7075b94e9ae6.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef21e209131cea4311c.md>)

[Implementation](<https://github.com/muzairkhattak/multimodal-prompt-learning>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoOpOp

Source Domain Accuracy (ImageNet): 70.62. Result ID: 6a058ceb47f34ce924ecaaad.

[Reporting paper](<https://www.sota2.com/research/paper/6a055740dbc836b87d828e74.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8c1e209131cea3a831.md>)

[Implementation](<https://github.com/KaiyangZhou/CoOp>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RPO

Source Domain Accuracy (ImageNet): 69.69. Result ID: 6a058ceb47f34ce924ecaaaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a055740dbc836b87d828e74.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f558.md>)

[Implementation](<https://github.com/mlvlab/RPO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CLIP-Adapter

Source Domain Accuracy (ImageNet): 68.64. Result ID: 6a058ceb47f34ce924ecaaae.

[Reporting paper](<https://www.sota2.com/research/paper/6a055740dbc836b87d828e74.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77921e209131cea7403b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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