# EEG-to-Image Reconstruction on THINGS-EEG2 200-sample (test)

Source: [EEG-to-Image Reconstruction on THINGS-EEG2 200-sample (test)](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test>)

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

Data updated: 2026-05-26T07:18:10.553Z

Evaluation of models performing EEG-to-Image Reconstruction using the test split of the THINGS-EEG2 200-sample dataset. Performance is assessed using metrics such as SSIM, Pixel Correlation, and representation similarity scores derived from various pre-trained networks (CLIP, AlexNet, SwAV, Inception).

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 | EEG-to-Image Reconstruction |
| Dataset (including any stated split) | THINGS-EEG2 200-sample (test) |
| Metric | CLIP-L/14 Two-way ID |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 1 of 1 |
| 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

- [CLIP-L/14 Two-way ID](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=CLIP-L%2F14%20Two-way%20ID>): Higher is better; unit: SCALAR.

- [CLIP-H/14 Two-way ID](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=CLIP-H%2F14%20Two-way%20ID>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [Pixel Correlation](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=Pixel%20Correlation>): Higher is better; unit: SCALAR.

- [AlexNet-2 Two-way ID](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=AlexNet-2%20Two-way%20ID>): Higher is better; unit: SCALAR.

- [AlexNet-5 Two-way ID](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=AlexNet-5%20Two-way%20ID>): Higher is better; unit: SCALAR.

- [Inception Two-way ID](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=Inception%20Two-way%20ID>): Higher is better; unit: SCALAR.

- [EfficientNet Correlation Similarity](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=EfficientNet%20Correlation%20Similarity>): Higher is better; unit: SCALAR.

- [SwAV Correlation Similarity](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md?metric=SwAV%20Correlation%20Similarity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CLIP-L/14 Two-way ID | Result date | Report paper |
| --- | --- | --- | --- |
| Brain-to-Image system | 0.87 | Not recorded | 6a152902dbd7150506f7ddd8 |

### Brain-to-Image system

CLIP-L/14 Two-way ID: 0.87. Result ID: 6a154918fbc373592c0c356c.

[Reporting paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd8.md>)

Recorded evaluation configuration: {"evaluation":"averaged over 10 random seeds"}. This record does not assert independent reproduction.

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