# Semi-supervised Learning on ImageNet 1% labels (train val)

Source: [Semi-supervised Learning on ImageNet 1% labels (train val)](<https://www.sota2.com/research/sota/semi-supervised-learning-on-imagenet-1-percent-labels-train-val>)

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

Data updated: 2026-02-26T06:06:44.965Z

Evaluation of Semi-supervised Learning performance using the combined training and validation splits of the ImageNet 1% labeled subset, measured by Top-1 and Top-5 accuracy.

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 | Semi-supervised Learning |
| Dataset (including any stated split) | ImageNet 1% labels (train val) |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Top-1 Acc](<https://www.sota2.com/research/sota/semi-supervised-learning-on-imagenet-1-percent-labels-train-val.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

- [Top-5 Acc](<https://www.sota2.com/research/sota/semi-supervised-learning-on-imagenet-1-percent-labels-train-val.md?metric=Top-5%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Matrix-SSL | 45.158 | Not recorded | 68fa74c81e209131cea63c61 |
| MEC | 44.442 | Not recorded | 68fa74c81e209131cea63c61 |

### Matrix-SSL

Top-1 Acc: 45.158. Result ID: 699367623a6c31484915b2d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c81e209131cea63c61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c81e209131cea63c61.md>)

[Implementation](<https://github.com/yifanzhang-pro/Matrix-SSL>)

Recorded evaluation configuration: {"Pre-training Epochs":"100","Backbone":"ResNet-50","Evaluation Protocol":"Semi-supervised"}. This record does not assert independent reproduction.

### MEC

Top-1 Acc: 44.442. Result ID: 699367623a6c31484915b2d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c81e209131cea63c61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bc6b.md>)

Recorded evaluation configuration: {"Pre-training Epochs":"100","Backbone":"ResNet-50","Evaluation Protocol":"Semi-supervised"}. This record does not assert independent reproduction.

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