# Few-shot Image Classification on StanfordCars (test)

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

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

Data updated: 2026-02-26T05:34:00.051Z

Evaluation of Few-shot Image Classification performance on the test split of the Stanford Cars dataset, reporting accuracy across various shot settings (1-shot, 2-shot, etc.).

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) | StanfordCars (test) |
| Metric | Accuracy (1-shot) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 29 of 29 |
| 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-stanfordcars-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-stanfordcars-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-stanfordcars-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-stanfordcars-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-stanfordcars-test.md?metric=Accuracy%20(16-shot)>): Higher is better; unit: PERCENT.

- [Accuracy (5-shot)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-stanfordcars-test.md?metric=Accuracy%20(5-shot)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (1-shot) | Result date | Report paper |
| --- | --- | --- | --- |
| C2-Net | 81.29 | Not recorded | 69520af053fdd5c36173d58a |
| CausalFSFG | 79.96 | Not recorded | 69520af053fdd5c36173d58a |
| Bi-FRN | 75.74 | Not recorded | 69520af053fdd5c36173d58a |
| PromptSRC | 69.4 | Not recorded | 68fa77a11e209131cea747a9 |
| PromptSRC | 69.4 | Not recorded | 68fa78871e209131cea78dd1 |
| MMRL | 68.7 | Not recorded | 68fa77a11e209131cea747a9 |
| MMRL | 68.7 | Not recorded | 68fa78871e209131cea78dd1 |
| MMRL++ | 68.2 | Not recorded | 68fa78871e209131cea78dd1 |
| MMA | 67.87 | Not recorded | 68fa77a11e209131cea747a9 |
| MMA | 67.87 | Not recorded | 68fa78871e209131cea78dd1 |
| FRN | 67.48 | Not recorded | 69520af053fdd5c36173d58a |
| CoOp | 67.43 | Not recorded | 68fa77a11e209131cea747a9 |
| CoOp | 67.43 | Not recorded | 68fa78871e209131cea78dd1 |
| CoCoOp | 67.22 | Not recorded | 68fa77a11e209131cea747a9 |
| CoCoOp | 67.22 | Not recorded | 68fa78871e209131cea78dd1 |
| MaPLe | 66.6 | Not recorded | 68fa77a11e209131cea747a9 |
| MaPLe | 66.6 | Not recorded | 68fa78871e209131cea78dd1 |
| CTX | 66.35 | Not recorded | 69520af053fdd5c36173d58a |
| PARN | 66.01 | Not recorded | 69520af053fdd5c36173d58a |
| FRN+TDM | 65.67 | Not recorded | 69520af053fdd5c36173d58a |
| DeepEMD | 61.63 | Not recorded | 69520af053fdd5c36173d58a |
| SAML | 61.07 | Not recorded | 69520af053fdd5c36173d58a |
| LRPABN | 60.28 | Not recorded | 69520af053fdd5c36173d58a |
| ProtoNet | 50.88 | Not recorded | 69520af053fdd5c36173d58a |
| Relation | 46.04 | Not recorded | 69520af053fdd5c36173d58a |
| BSNet(D&C) | 40.89 | Not recorded | 69520af053fdd5c36173d58a |
| Linear probe CLIP | 35.66 | Not recorded | 68fa77a11e209131cea747a9 |
| Linear probe CLIP | 35.66 | Not recorded | 68fa78871e209131cea78dd1 |
| DN4 | 34.12 | Not recorded | 69520af053fdd5c36173d58a |

### C2-Net

Accuracy (1-shot): 81.29. Result ID: 69980e855698665ec46836ae.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"AAAI 2024"}. This record does not assert independent reproduction.

### CausalFSFG

Accuracy (1-shot): 79.96. Result ID: 69980e855698665ec46836af.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4"}. This record does not assert independent reproduction.

### Bi-FRN

Accuracy (1-shot): 75.74. Result ID: 69980e855698665ec46836ad.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5e1e209131cea3f696.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"AAAI 2023"}. This record does not assert independent reproduction.

### PromptSRC

Accuracy (1-shot): 69.4. Result ID: 699557e73badfaffe648bbf0.

[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): 69.4. Result ID: 699590bd3badfaffe68adbfd.

[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.

### MMRL

Accuracy (1-shot): 68.7. Result ID: 699557e73badfaffe648bbf2.

[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): 68.7. Result ID: 699590bd3badfaffe68adbff.

[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.

### MMRL++

Accuracy (1-shot): 68.2. Result ID: 699590bd3badfaffe68adc00.

[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.

### MMA

Accuracy (1-shot): 67.87. Result ID: 699557e73badfaffe648bbf1.

[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): 67.87. Result ID: 699590bd3badfaffe68adbfe.

[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.

### FRN

Accuracy (1-shot): 67.48. Result ID: 69980e855698665ec46836ab.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d51e209131cea24789.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"CVPR 2021"}. This record does not assert independent reproduction.

### CoOp

Accuracy (1-shot): 67.43. Result ID: 699557e73badfaffe648bbed.

[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): 67.43. Result ID: 699590bd3badfaffe68adbfa.

[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.

### CoCoOp

Accuracy (1-shot): 67.22. Result ID: 699557e73badfaffe648bbee.

[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): 67.22. Result ID: 699590bd3badfaffe68adbfb.

[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.

### MaPLe

Accuracy (1-shot): 66.6. Result ID: 699557e73badfaffe648bbef.

[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): 66.6. Result ID: 699590bd3badfaffe68adbfc.

[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.

### CTX

Accuracy (1-shot): 66.35. Result ID: 69980e855698665ec46836aa.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694a1e209131cea213be.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"NeurIPS 2020"}. This record does not assert independent reproduction.

### PARN

Accuracy (1-shot): 66.01. Result ID: 69980e855698665ec46836a5.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66541e209131cea0f870.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"ICCV 2019"}. This record does not assert independent reproduction.

### FRN+TDM

Accuracy (1-shot): 65.67. Result ID: 69980e855698665ec46836ac.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf81e209131cea36fa3.md>)

[Implementation](<https://github.com/leesb7426/CVPR2022-Task-Discrepancy-Maximization-for-Fine-grained-Few-Shot-Classification>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"CVPR 2022"}. This record does not assert independent reproduction.

### DeepEMD

Accuracy (1-shot): 61.63. Result ID: 69980e855698665ec46836a7.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"CVPR 2020"}. This record does not assert independent reproduction.

### SAML

Accuracy (1-shot): 61.07. Result ID: 69980e855698665ec46836a6.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"ICCV 2019"}. This record does not assert independent reproduction.

### LRPABN

Accuracy (1-shot): 60.28. Result ID: 69980e855698665ec46836a8.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697d1e209131cea22664.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"TMM 2021"}. This record does not assert independent reproduction.

### ProtoNet

Accuracy (1-shot): 50.88. Result ID: 69980e855698665ec46836a2.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa636e1e209131ce9febd3.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"NeurIPS 2017"}. This record does not assert independent reproduction.

### Relation

Accuracy (1-shot): 46.04. Result ID: 69980e855698665ec46836a3.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64301e209131cea03588.md>)

[Implementation](<https://github.com/lzrobots/DeepEmbeddingModel_ZSL>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"CVPR 2018"}. This record does not assert independent reproduction.

### BSNet(D&C)

Accuracy (1-shot): 40.89. Result ID: 69980e855698665ec46836a9.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69381e209131cea20e9c.md>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"TIP 2021"}. This record does not assert independent reproduction.

### Linear probe CLIP

Accuracy (1-shot): 35.66. Result ID: 699557e73badfaffe648bbec.

[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): 35.66. Result ID: 699590bd3badfaffe68adbf9.

[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.

### DN4

Accuracy (1-shot): 34.12. Result ID: 69980e855698665ec46836a4.

[Reporting paper](<https://www.sota2.com/research/paper/69520af053fdd5c36173d58a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b80d.md>)

[Implementation](<https://github.com/WenbinLee/DN4.git>)

Recorded evaluation configuration: {"Backbone":"Conv-4","Published In":"CVPR 2019"}. This record does not assert independent reproduction.

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