# Image Classification on iNaturalist finest sub-category level (full)

Source: [Image Classification on iNaturalist finest sub-category level (full)](<https://www.sota2.com/research/sota/image-classification-on-inaturalist-finest-sub-category-level-full>)

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

Data updated: 2026-02-26T06:06:58.774Z

Evaluation of Image Classification performance on the full set of finest sub-categories of the iNaturalist dataset, typically measured by Top-1 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 | Image Classification |
| Dataset (including any stated split) | iNaturalist finest sub-category level (full) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-inaturalist-finest-sub-category-level-full.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HiMulConE | 0.594 | Not recorded | 68fa6c601e209131cea33ab3 |
| Guided | 0.5733 | Not recorded | 68fa6c601e209131cea33ab3 |
| SupCon | 0.5728 | Not recorded | 68fa6c601e209131cea33ab3 |
| Cross Entropy | 0.5686 | Not recorded | 68fa6c601e209131cea33ab3 |
| SimCLR | 0.5402 | Not recorded | 68fa6c601e209131cea33ab3 |

### HiMulConE

Top-1 Accuracy: 0.594. Result ID: 698f0dd73a6c314849f548ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

[Implementation](<https://github.com/salesforce/hierarchicalContrastiveLearning>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Protocol":"Fine-tuned","Evaluation":"Linear classifier"}. This record does not assert independent reproduction.

### Guided

Top-1 Accuracy: 0.5733. Result ID: 698f0dd73a6c314849f548eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b511e209131cea2d988.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Protocol":"Fine-tuned","Evaluation":"Linear classifier"}. This record does not assert independent reproduction.

### SupCon

Top-1 Accuracy: 0.5728. Result ID: 698f0dd73a6c314849f548ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Protocol":"Fine-tuned","Evaluation":"Linear classifier"}. This record does not assert independent reproduction.

### Cross Entropy

Top-1 Accuracy: 0.5686. Result ID: 698f0dd73a6c314849f548e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Protocol":"Fine-tuned","Evaluation":"Linear classifier"}. This record does not assert independent reproduction.

### SimCLR

Top-1 Accuracy: 0.5402. Result ID: 698f0dd73a6c314849f548e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c601e209131cea33ab3.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Protocol":"Fine-tuned","Evaluation":"Linear classifier"}. This record does not assert independent reproduction.

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