# Hierarchical Image Classification on ImageNet

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

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

Data updated: 2026-02-26T05:48:33.472Z

Evaluation of Hierarchical Image Classification performance on the ImageNet dataset, measured using Leaf Accuracy and Hierarchical Classification Accuracy (HCA).

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 | Hierarchical Image Classification |
| Dataset (including any stated split) | ImageNet |
| Metric | Leaf Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

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

- [HCA](<https://www.sota2.com/research/sota/hierarchical-image-classification-on-imagenet.md?metric=HCA>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Leaf Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 68.36 | Not recorded | 68fa72ac1e209131cea57bf3 |
| CLIP | 63.31 | Not recorded | 68fa72ac1e209131cea57bf3 |
| CLIP | 62.3 | Not recorded | 68fa72ac1e209131cea57bf3 |
| CLIP | 59.81 | Not recorded | 68fa72ac1e209131cea57bf3 |

### CLIP

Leaf Accuracy: 68.36. Result ID: 699267ab3a6c3148490ebb1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57bf3.md>)

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

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

Recorded evaluation configuration: {"Encoder":"ViT-B16","K-shot":0,"w/ ProTeCt":"N/A","λ":"N/A","β":"N/A"}. This record does not assert independent reproduction.

### CLIP

Leaf Accuracy: 63.31. Result ID: 699267ab3a6c3148490ebb1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57bf3.md>)

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

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

Recorded evaluation configuration: {"Encoder":"ViT-B32","K-shot":0,"w/ ProTeCt":"N/A","λ":"N/A","β":"N/A"}. This record does not assert independent reproduction.

### CLIP

Leaf Accuracy: 62.3. Result ID: 699267ab3a6c3148490ebb1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57bf3.md>)

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

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

Recorded evaluation configuration: {"Encoder":"RN101","K-shot":0,"w/ ProTeCt":"N/A","λ":"N/A","β":"N/A"}. This record does not assert independent reproduction.

### CLIP

Leaf Accuracy: 59.81. Result ID: 699267ab3a6c3148490ebb1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57bf3.md>)

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

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

Recorded evaluation configuration: {"Encoder":"RN50","K-shot":0,"w/ ProTeCt":"N/A","λ":"N/A","β":"N/A"}. This record does not assert independent reproduction.

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