# Deep Clustering on Fashion-MNIST 60k samples (train test)

Source: [Deep Clustering on Fashion-MNIST 60k samples (train test)](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test>)

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

Data updated: 2026-02-26T06:02:47.991Z

Evaluation of Deep Clustering performance using the 60,000 sample train and test splits of the Fashion-MNIST dataset, reporting metrics such as SC, NMI, and ETP.

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 | Deep Clustering |
| Dataset (including any stated split) | Fashion-MNIST 60k samples (train test) |
| Metric | SC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [SC](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=SC>): Higher is better; unit: SCALAR.

- [NMI](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=NMI>): Higher is better; unit: SCALAR.

- [RL](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=RL>): Higher is better; unit: SCALAR.

- [RRL](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=RRL>): Higher is better; unit: SCALAR.

- [ETP](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=ETP>): Lower is better; unit: SCALAR.

- [CS (Count Pair)](<https://www.sota2.com/research/sota/deep-clustering-on-fashion-mnist-60k-samples-train-test.md?metric=CS%20(Count%20Pair)>): Higher is better; unit: OTHER.

## Recorded results

| Method | SC | Result date | Report paper |
| --- | --- | --- | --- |
| DCAM | 0.97 | Not recorded | 695c96f553fdd5c3617435b1 |
| DCEC | 0.923 | Not recorded | 695c96f553fdd5c3617435b1 |
| DCEC | 0.726 | Not recorded | 695c96f553fdd5c3617435b1 |
| DCAM | 0.712 | Not recorded | 695c96f553fdd5c3617435b1 |
| DCAM | 0.663 | Not recorded | 695c96f553fdd5c3617435b1 |
| EDCWRN | 0.483 | Not recorded | 695c96f553fdd5c3617435b1 |
| ClAM | 0.279 | Not recorded | 695c96f553fdd5c3617435b1 |
| DEKM | 0.26 | Not recorded | 695c96f553fdd5c3617435b1 |
| DEKM | 0.258 | Not recorded | 695c96f553fdd5c3617435b1 |
| Kmeans | 0.257 | Not recorded | 695c96f553fdd5c3617435b1 |
| Agglo | 0.201 | Not recorded | 695c96f553fdd5c3617435b1 |
| ClAM | 0.158 | Not recorded | 695c96f553fdd5c3617435b1 |
| Kmeans | 0.154 | Not recorded | 695c96f553fdd5c3617435b1 |
| Agglo | 0.109 | Not recorded | 695c96f553fdd5c3617435b1 |

### DCAM

SC: 0.97. Result ID: 6997f1e55698665ec44b3ea3.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### DCEC

SC: 0.923. Result ID: 6997f1e55698665ec44b3e9e.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### DCEC

SC: 0.726. Result ID: 6997f1e55698665ec44b3e9f.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"RAE"}. This record does not assert independent reproduction.

### DCAM

SC: 0.712. Result ID: 6997f1e55698665ec44b3ea5.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"RAE"}. This record does not assert independent reproduction.

### DCAM

SC: 0.663. Result ID: 6997f1e55698665ec44b3ea4.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"EAE"}. This record does not assert independent reproduction.

### EDCWRN

SC: 0.483. Result ID: 6997f1e55698665ec44b3ea2.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### ClAM

SC: 0.279. Result ID: 6997f1e55698665ec44b3e9d.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d2b.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### DEKM

SC: 0.26. Result ID: 6997f1e55698665ec44b3ea0.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b41b.md>)

[Implementation](<https://github.com/spdj2271/DEKM>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### DEKM

SC: 0.258. Result ID: 6997f1e55698665ec44b3ea1.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b41b.md>)

[Implementation](<https://github.com/spdj2271/DEKM>)

Recorded evaluation configuration: {"AE Architecture":"RAE"}. This record does not assert independent reproduction.

### Kmeans

SC: 0.257. Result ID: 6997f1e55698665ec44b3e99.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### Agglo

SC: 0.201. Result ID: 6997f1e55698665ec44b3e9b.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"CAE"}. This record does not assert independent reproduction.

### ClAM

SC: 0.158. Result ID: 6997f1e55698665ec44b3e9c.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d2b.md>)

Recorded evaluation configuration: {"AE Architecture":"NAE"}. This record does not assert independent reproduction.

### Kmeans

SC: 0.154. Result ID: 6997f1e55698665ec44b3e98.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"NAE"}. This record does not assert independent reproduction.

### Agglo

SC: 0.109. Result ID: 6997f1e55698665ec44b3e9a.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f553fdd5c3617435b1.md>)

Recorded evaluation configuration: {"AE Architecture":"NAE"}. This record does not assert independent reproduction.

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