# Image Classification on Unbalanced IFCB Plankton Dataset (test)

Source: [Image Classification on Unbalanced IFCB Plankton Dataset (test)](<https://www.sota2.com/research/sota/image-classification-on-unbalanced-ifcb-plankton-dataset-test>)

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

Data updated: 2026-02-26T05:31:33.332Z

Evaluation of Image Classification performance on the test split of the Unbalanced IFCB Plankton Dataset, measured using Accuracy and Macro F1.

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) | Unbalanced IFCB Plankton Dataset (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-unbalanced-ifcb-plankton-dataset-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro F1](<https://www.sota2.com/research/sota/image-classification-on-unbalanced-ifcb-plankton-dataset-test.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EfficientNet-B0 | 97.61 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| ResNet-50 | 97.59 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| EfficientNet-B3 | 96.13 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| Our Diffusion | 91.45 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| EfficientNet-V2-S | 91 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| ViT-B/16 | 90.5 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| MLP on features | 86.51 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| Masked Autoencoders | 82.07 | Not recorded | 69705ddee25ad2fa9d1ed6ea |
| DINOv3 | 79.09 | Not recorded | 69705ddee25ad2fa9d1ed6ea |

### EfficientNet-B0

Accuracy: 97.61. Result ID: 6997a7645698665ec4fd8050.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b521.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"4M"}. This record does not assert independent reproduction.

### ResNet-50

Accuracy: 97.59. Result ID: 6997a7645698665ec4fd804f.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"25.5M"}. This record does not assert independent reproduction.

### EfficientNet-B3

Accuracy: 96.13. Result ID: 6997a7645698665ec4fd8051.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b521.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"11M"}. This record does not assert independent reproduction.

### Our Diffusion

Accuracy: 91.45. Result ID: 6997a7645698665ec4fd8056.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"57M"}. This record does not assert independent reproduction.

### EfficientNet-V2-S

Accuracy: 91. Result ID: 6997a7645698665ec4fd8052.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b521.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"22.5M"}. This record does not assert independent reproduction.

### ViT-B/16

Accuracy: 90.5. Result ID: 6997a7645698665ec4fd8053.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"87M"}. This record does not assert independent reproduction.

### MLP on features

Accuracy: 86.51. Result ID: 6997a7645698665ec4fd804e.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear probe","Params":"0.1M"}. This record does not assert independent reproduction.

### Masked Autoencoders

Accuracy: 82.07. Result ID: 6997a7645698665ec4fd8054.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

Recorded evaluation configuration: {"backbone":"ViT-B/16","Evaluation Protocol":"Linear probe","Params":"87M"}. This record does not assert independent reproduction.

### DINOv3

Accuracy: 79.09. Result ID: 6997a7645698665ec4fd8055.

[Reporting paper](<https://www.sota2.com/research/paper/69705ddee25ad2fa9d1ed6ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a931e209131cea83fc5.md>)

Recorded evaluation configuration: {"backbone":"ViT-B/16","Evaluation Protocol":"Linear probe","Params":"87M"}. This record does not assert independent reproduction.

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