# Hierarchical Generative Modeling on Fashion-Mnist

Source: [Hierarchical Generative Modeling on Fashion-Mnist](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist>)

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

Data updated: 2026-05-08T10:49:20.922Z

Evaluation of hierarchical generative models on the Fashion-Mnist dataset, assessed using metrics including DP, LP, ACC, NMI, and various likelihood measures.

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 Generative Modeling |
| Dataset (including any stated split) | Fashion-Mnist |
| Metric | DP |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [DP](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=DP>): Higher is better; unit: SCALAR.

- [LP](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=LP>): Higher is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=Accuracy>): Higher is better; unit: SCALAR.

- [NMI](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=NMI>): Higher is better; unit: SCALAR.

- [Reconstruction Likelihood (RL)](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=Reconstruction%20Likelihood%20(RL)>): Higher is better; unit: SCALAR.

- [Log Likelihood (LL)](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=Log%20Likelihood%20(LL)>): Higher is better; unit: SCALAR.

- [Average Score](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | DP | Result date | Report paper |
| --- | --- | --- | --- |
| HDTree | 57.4 | Not recorded | 68fa5f821e209131ce9ea80a |
| TreeVAE | 53.4 | Not recorded | 68fa5f821e209131ce9ea80a |
| LadderVAE | 49.5 | Not recorded | 68fa5f821e209131ce9ea80a |
| HDTree | 47.7 | Not recorded | 68fa5f821e209131ce9ea80a |
| Agg | 45 | Not recorded | 68fa5f821e209131ce9ea80a |
| DeepECT | 44.9 | Not recorded | 68fa5f821e209131ce9ea80a |
| VAE | 44.3 | Not recorded | 68fa5f821e209131ce9ea80a |

### HDTree

DP: 57.4. Result ID: 69fdbfa647f34ce924e178bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

Recorded evaluation configuration: {"Agglomerative Clustering":"False"}. This record does not assert independent reproduction.

### TreeVAE

DP: 53.4. Result ID: 69fdbfa647f34ce924e178b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea50142.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LadderVAE

DP: 49.5. Result ID: 69fdbfa647f34ce924e178b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627d1e209131ce9f98cf.md>)

Recorded evaluation configuration: {"Agglomerative Clustering":"True"}. This record does not assert independent reproduction.

### HDTree

DP: 47.7. Result ID: 69fdbfa647f34ce924e178ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

Recorded evaluation configuration: {"Agglomerative Clustering":"True"}. This record does not assert independent reproduction.

### Agg

DP: 45. Result ID: 69fdbfa647f34ce924e178b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60591e209131ce9ef091.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepECT

DP: 44.9. Result ID: 69fdbfa647f34ce924e178b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VAE

DP: 44.3. Result ID: 69fdbfa647f34ce924e178b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f821e209131ce9ea80a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fe34.md>)

Recorded evaluation configuration: {"Agglomerative Clustering":"True"}. This record does not assert independent reproduction.

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