# Few-shot Image Classification on ImageNet (test)

Source: [Few-shot Image Classification on ImageNet (test)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test>)

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

Data updated: 2026-02-26T05:34:00.153Z

Evaluation of few-shot image classification performance on the test split of the standard ImageNet dataset, measured across various shot counts (1, 2, 4, 8, 16 shots).

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 | Few-shot Image Classification |
| Dataset (including any stated split) | ImageNet (test) |
| Metric | Accuracy (1-shot) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 22 of 22 |
| 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

- [Accuracy (1-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Accuracy%20(1-shot)>): Higher is better; unit: PERCENT.

- [Accuracy (2-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Accuracy%20(2-shot)>): Higher is better; unit: PERCENT.

- [Accuracy (4-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Accuracy%20(4-shot)>): Higher is better; unit: PERCENT.

- [Accuracy (8-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Accuracy%20(8-shot)>): Higher is better; unit: PERCENT.

- [Accuracy (16-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Accuracy%20(16-shot)>): Higher is better; unit: PERCENT.

- [Top-1 Acc](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-test.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (1-shot) | Result date | Report paper |
| --- | --- | --- | --- |
| MMRL++ | 70.03 | Not recorded | 68fa78871e209131cea78dd1 |
| CoCoOp | 69.43 | Not recorded | 68fa77a11e209131cea747a9 |
| CoCoOp | 69.43 | Not recorded | 68fa78871e209131cea78dd1 |
| MMA | 69.17 | Not recorded | 68fa77a11e209131cea747a9 |
| MMA | 69.17 | Not recorded | 68fa78871e209131cea78dd1 |
| MMRL | 69 | Not recorded | 68fa77a11e209131cea747a9 |
| MMRL | 69 | Not recorded | 68fa78871e209131cea78dd1 |
| PromptSRC | 68.13 | Not recorded | 68fa77a11e209131cea747a9 |
| PromptSRC | 68.13 | Not recorded | 68fa78871e209131cea78dd1 |
| CoOp | 66.33 | Not recorded | 68fa77a11e209131cea747a9 |
| CoOp | 66.33 | Not recorded | 68fa78871e209131cea78dd1 |
| MaPLe | 62.67 | Not recorded | 68fa77a11e209131cea747a9 |
| MaPLe | 62.67 | Not recorded | 68fa78871e209131cea78dd1 |
| Linear probe CLIP | 32.13 | Not recorded | 68fa77a11e209131cea747a9 |
| Linear probe CLIP | 32.13 | Not recorded | 68fa78871e209131cea78dd1 |

### MMRL++

Accuracy (1-shot): 70.03. Result ID: 699590bd3badfaffe68adbe8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

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

### CoCoOp

Accuracy (1-shot): 69.43. Result ID: 699557e73badfaffe648bbd9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a11e209131cea747a9.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.

### CoCoOp

Accuracy (1-shot): 69.43. Result ID: 699590bd3badfaffe68adbe3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.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.

### MMA

Accuracy (1-shot): 69.17. Result ID: 699557e73badfaffe648bbdc.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c21e209131cea6392b.md>)

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

### MMA

Accuracy (1-shot): 69.17. Result ID: 699590bd3badfaffe68adbe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c21e209131cea6392b.md>)

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

### MMRL

Accuracy (1-shot): 69. Result ID: 699557e73badfaffe648bbdd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a11e209131cea747a9.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.

### MMRL

Accuracy (1-shot): 69. Result ID: 699590bd3badfaffe68adbe7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

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

### PromptSRC

Accuracy (1-shot): 68.13. Result ID: 699557e73badfaffe648bbdb.

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

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

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

### PromptSRC

Accuracy (1-shot): 68.13. Result ID: 699590bd3badfaffe68adbe5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

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

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

### CoOp

Accuracy (1-shot): 66.33. Result ID: 699557e73badfaffe648bbd8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a11e209131cea747a9.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.

### CoOp

Accuracy (1-shot): 66.33. Result ID: 699590bd3badfaffe68adbe2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.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.

### MaPLe

Accuracy (1-shot): 62.67. Result ID: 699557e73badfaffe648bbda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a11e209131cea747a9.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.

### MaPLe

Accuracy (1-shot): 62.67. Result ID: 699590bd3badfaffe68adbe4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.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.

### Linear probe CLIP

Accuracy (1-shot): 32.13. Result ID: 699557e73badfaffe648bbd7.

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

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

### Linear probe CLIP

Accuracy (1-shot): 32.13. Result ID: 699590bd3badfaffe68adbe1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78871e209131cea78dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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.
