# Latent Isomorphism on smallNORB

Source: [Latent Isomorphism on smallNORB](<https://www.sota2.com/research/sota/latent-isomorphism-on-smallnorb>)

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

Data updated: 2026-03-04T17:15:11.216Z

Evaluation of latent isomorphism performance on the smallNORB dataset, reporting metrics such as MSE, R^2, DSC, and NOS@10.

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 | Latent Isomorphism |
| Dataset (including any stated split) | smallNORB |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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

- [MSE](<https://www.sota2.com/research/sota/latent-isomorphism-on-smallnorb.md?metric=MSE>): Lower is better; unit: SCALAR.

- [R^2](<https://www.sota2.com/research/sota/latent-isomorphism-on-smallnorb.md?metric=R%5E2>): Higher is better; unit: PERCENT.

- [DSC](<https://www.sota2.com/research/sota/latent-isomorphism-on-smallnorb.md?metric=DSC>): Higher is better; unit: PERCENT.

- [NOS@10](<https://www.sota2.com/research/sota/latent-isomorphism-on-smallnorb.md?metric=NOS%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| Social-JEPA | 0.036 | Not recorded | 69a7bc6b2d603e6de3e3d322 |
| MAE | 0.041 | Not recorded | 69a7bc6b2d603e6de3e3d322 |
| SimCLR | 0.112 | Not recorded | 69a7bc6b2d603e6de3e3d322 |
| MoCo v3 | 0.478 | Not recorded | 69a7bc6b2d603e6de3e3d322 |
| iBOT | 24.433 | Not recorded | 69a7bc6b2d603e6de3e3d322 |
| DINO | 93.641 | Not recorded | 69a7bc6b2d603e6de3e3d322 |

### Social-JEPA

MSE: 0.036. Result ID: 69a8688f6dbb7075b9503010.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

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

### MAE

MSE: 0.041. Result ID: 69a8688f6dbb7075b9503014.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

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

### SimCLR

MSE: 0.112. Result ID: 69a8688f6dbb7075b9503015.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

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

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

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

### MoCo v3

MSE: 0.478. Result ID: 69a8688f6dbb7075b9503012.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2903d.md>)

[Implementation](<https://github.com/facebookresearch/moco-v3>)

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

### iBOT

MSE: 24.433. Result ID: 69a8688f6dbb7075b9503013.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bb51e209131cea2fbe0.md>)

[Implementation](<https://github.com/bytedance/ibot>)

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

### DINO

MSE: 93.641. Result ID: 69a8688f6dbb7075b9503011.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc6b2d603e6de3e3d322.md>)

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

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

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

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