# Few-shot classification on Plantae

Source: [Few-shot classification on Plantae](<https://www.sota2.com/research/sota/few-shot-classification-on-plantae>)

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

Data updated: 2026-02-26T05:28:44.319Z

Evaluation of Few-shot Classification performance on the Plantae dataset, reporting accuracy.

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 classification |
| Dataset (including any stated split) | Plantae |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 41 of 41 |
| 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](<https://www.sota2.com/research/sota/few-shot-classification-on-plantae.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Supervised | 72.91 | Not recorded | 68fa6eaa1e209131cea41376 |
| PsCo | 71.14 | Not recorded | 68fa6eaa1e209131cea41376 |
| PsCo | 69.17 | Not recorded | 68fa6eaa1e209131cea41376 |
| PsCo | 64.53 | Not recorded | 68fa6eaa1e209131cea41376 |
| PsCo | 61.55 | Not recorded | 68fa6eaa1e209131cea41376 |
| MoCo v2 | 61.36 | Not recorded | 68fa6eaa1e209131cea41376 |
| BYOL | 56.86 | Not recorded | 68fa6eaa1e209131cea41376 |
| MoCo v2 | 56.24 | Not recorded | 68fa6eaa1e209131cea41376 |
| MoCo v2 | 55.45 | Not recorded | 68fa6eaa1e209131cea41376 |
| SimCLR | 54.92 | Not recorded | 68fa6eaa1e209131cea41376 |
| MAML | 54.86 | Not recorded | 68fa6eaa1e209131cea41376 |
| ProtoNets | 54.29 | Not recorded | 68fa6eaa1e209131cea41376 |
| SWAV | 54.03 | Not recorded | 68fa6eaa1e209131cea41376 |
| GNN (FT) | 53.85 | Not recorded | 68fa67391e209131cea1507c |
| PsCo | 52.72 | Not recorded | 68fa6eaa1e209131cea41376 |
| GNN | 52.53 | Not recorded | 68fa67391e209131cea1507c |
| MAML | 47.33 | Not recorded | 68fa6eaa1e209131cea41376 |
| MatchingNet | 46.53 | Not recorded | 68fa67391e209131cea1507c |
| MetaOptNet-SVM-trainval | 46.48 | Not recorded | 68fa67391e209131cea1507c |
| Meta-SVEBM | 46.22 | Not recorded | 68fa6eaa1e209131cea41376 |
| ProtoNets | 45.89 | Not recorded | 68fa6eaa1e209131cea41376 |
| RelationNet (FT) | 45.08 | Not recorded | 68fa67391e209131cea1507c |
| Meta-GMVAE | 45.02 | Not recorded | 68fa6eaa1e209131cea41376 |
| RelationNet | 44 | Not recorded | 68fa67391e209131cea1507c |
| MoCo v2 | 43.97 | Not recorded | 68fa6eaa1e209131cea41376 |
| SimCLR | 43.42 | Not recorded | 68fa6eaa1e209131cea41376 |
| SWAV | 42.68 | Not recorded | 68fa6eaa1e209131cea41376 |
| MatchingNet (FT) | 41.69 | Not recorded | 68fa67391e209131cea1507c |
| Meta-GMVAE | 38.27 | Not recorded | 68fa6eaa1e209131cea41376 |
| Meta-SVEBM | 38.12 | Not recorded | 68fa6eaa1e209131cea41376 |

### Supervised

Accuracy: 72.91. Result ID: 699038e83a6c314849ff02c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### PsCo

Accuracy: 71.14. Result ID: 699038e83a6c314849ff02bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Implementation](<https://github.com/alinlab/PsCo>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Base Method":"BYOL","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### PsCo

Accuracy: 69.17. Result ID: 699038e83a6c314849ff02bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Implementation](<https://github.com/alinlab/PsCo>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Base Method":"MoCo v2","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### PsCo

Accuracy: 64.53. Result ID: 699038e83a6c314849ff03c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Implementation](<https://github.com/alinlab/PsCo>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### PsCo

Accuracy: 61.55. Result ID: 699038e83a6c314849ff02bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Implementation](<https://github.com/alinlab/PsCo>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Base Method":"MoCo v2","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### MoCo v2

Accuracy: 61.36. Result ID: 699038e83a6c314849ff02bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### BYOL

Accuracy: 56.86. Result ID: 699038e83a6c314849ff02be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b1e9.md>)

[Implementation](<https://github.com/deepmind/deepmind-research/tree/byol>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### MoCo v2

Accuracy: 56.24. Result ID: 699038e83a6c314849ff02ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Evaluation protocol":"5-way 5-shot"}. This record does not assert independent reproduction.

### MoCo v2

Accuracy: 55.45. Result ID: 699038e83a6c314849ff03bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### SimCLR

Accuracy: 54.92. Result ID: 699038e83a6c314849ff03ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

[Implementation](<https://github.com/google-research/simclr>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### MAML

Accuracy: 54.86. Result ID: 699038e83a6c314849ff03c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63861e209131ce9ff3e8.md>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### ProtoNets

Accuracy: 54.29. Result ID: 699038e83a6c314849ff03c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

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

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### SWAV

Accuracy: 54.03. Result ID: 699038e83a6c314849ff03be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faec.md>)

[Implementation](<https://github.com/facebookresearch/swav>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### GNN (FT)

Accuracy: 53.85. Result ID: 698d22fb8b517eb4331f475d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":true}. This record does not assert independent reproduction.

### PsCo

Accuracy: 52.72. Result ID: 699038e83a6c314849ff03bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Implementation](<https://github.com/alinlab/PsCo>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### GNN

Accuracy: 52.53. Result ID: 698d22fb8b517eb4331f475c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":false}. This record does not assert independent reproduction.

### MAML

Accuracy: 47.33. Result ID: 699038e83a6c314849ff03c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63861e209131ce9ff3e8.md>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### MatchingNet

Accuracy: 46.53. Result ID: 698d22fb8b517eb4331f4758.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":false}. This record does not assert independent reproduction.

### MetaOptNet-SVM-trainval

Accuracy: 46.48. Result ID: 698d22fb8b517eb4331f4757.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a91e209131cea0bba9.md>)

[Implementation](<https://github.com/kjunelee/MetaOptNet>)

Recorded evaluation configuration: {"Backbone":"ResNet-12","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":false}. This record does not assert independent reproduction.

### Meta-SVEBM

Accuracy: 46.22. Result ID: 699038e83a6c314849ff03b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### ProtoNets

Accuracy: 45.89. Result ID: 699038e83a6c314849ff03c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

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

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### RelationNet (FT)

Accuracy: 45.08. Result ID: 698d22fb8b517eb4331f475b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":true}. This record does not assert independent reproduction.

### Meta-GMVAE

Accuracy: 45.02. Result ID: 699038e83a6c314849ff03b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":20,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### RelationNet

Accuracy: 44. Result ID: 698d22fb8b517eb4331f475a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":false}. This record does not assert independent reproduction.

### MoCo v2

Accuracy: 43.97. Result ID: 699038e83a6c314849ff03bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### SimCLR

Accuracy: 43.42. Result ID: 699038e83a6c314849ff03b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

[Implementation](<https://github.com/google-research/simclr>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### SWAV

Accuracy: 42.68. Result ID: 699038e83a6c314849ff03bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faec.md>)

[Implementation](<https://github.com/facebookresearch/swav>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### MatchingNet (FT)

Accuracy: 41.69. Result ID: 698d22fb8b517eb4331f4759.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea1507c.md>)

[Implementation](<https://github.com/hytseng0509/CrossDomainFewShot>)

Recorded evaluation configuration: {"Backbone":"ResNet-10","Training Dataset":"mini-ImageNet","FT (Feature-wise Transformation)":true}. This record does not assert independent reproduction.

### Meta-GMVAE

Accuracy: 38.27. Result ID: 699038e83a6c314849ff03b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

### Meta-SVEBM

Accuracy: 38.12. Result ID: 699038e83a6c314849ff03b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41376.md>)

Recorded evaluation configuration: {"way":5,"shot":5,"Backbone":"Conv5","Pre-trained":"miniImageNet"}. This record does not assert independent reproduction.

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