# Unsupervised Image Classification on ImageNet Superclasses (29 classes) WordNet hierarchy (val)

Source: [Unsupervised Image Classification on ImageNet Superclasses (29 classes) WordNet hierarchy (val)](<https://www.sota2.com/research/sota/unsupervised-image-classification-on-imagenet-superclasses-29-classes-wordnet-hierarchy-val>)

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

Data updated: 2026-02-26T05:28:23.255Z

Evaluation of Unsupervised Image Classification performance using the 29 specific superclasses defined by the WordNet hierarchy on the validation split of ImageNet.

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 | Unsupervised Image Classification |
| Dataset (including any stated split) | ImageNet Superclasses (29 classes) WordNet hierarchy (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/unsupervised-image-classification-on-imagenet-superclasses-29-classes-wordnet-hierarchy-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Self-Classifier | 79.7 | Not recorded | 68fa6cf61e209131cea36e46 |
| SCAN | 79.3 | Not recorded | 68fa6cf61e209131cea36e46 |
| OBoW | 76.5 | Not recorded | 68fa6cf61e209131cea36e46 |
| MoCoV2 | 72.8 | Not recorded | 68fa6cf61e209131cea36e46 |
| BarlowT | 72.1 | Not recorded | 68fa6cf61e209131cea36e46 |
| DINO | 71.3 | Not recorded | 68fa6cf61e209131cea36e46 |
| SwAV | 69.4 | Not recorded | 68fa6cf61e209131cea36e46 |
| SeLa | 44.9 | Not recorded | 68fa6cf61e209131cea36e46 |

### Self-Classifier

Accuracy: 79.7. Result ID: 698f6f253a6c314849f88a06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Implementation](<https://github.com/elad-amrani/self-classifier>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### SCAN

Accuracy: 79.3. Result ID: 698f6f253a6c314849f88a05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18ae5.md>)

[Implementation](<https://www.sota2.com/here>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Pre-training":"ImageNet-pretrained"}. This record does not assert independent reproduction.

### OBoW

Accuracy: 76.5. Result ID: 698f6f253a6c314849f88a02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c89f.md>)

[Implementation](<https://github.com/valeoai/obow>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"k-means classifier"}. This record does not assert independent reproduction.

### MoCoV2

Accuracy: 72.8. Result ID: 698f6f253a6c314849f88a00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67371e209131cea14e30.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"k-means classifier"}. This record does not assert independent reproduction.

### BarlowT

Accuracy: 72.1. Result ID: 698f6f253a6c314849f88a03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f141e209131ce9e75ab.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"k-means classifier"}. This record does not assert independent reproduction.

### DINO

Accuracy: 71.3. Result ID: 698f6f253a6c314849f88a01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"k-means classifier"}. This record does not assert independent reproduction.

### SwAV

Accuracy: 69.4. Result ID: 698f6f253a6c314849f889ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"k-means classifier"}. This record does not assert independent reproduction.

### SeLa

Accuracy: 44.9. Result ID: 698f6f253a6c314849f88a04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cf61e209131cea36e46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671c1e209131cea144b1.md>)

[Implementation](<https://github.com/yukimasano/self-label>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Pre-training":"ImageNet-pretrained"}. This record does not assert independent reproduction.

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