# Image Classification on STL-10 (Donor/Receiver Accuracy Delta)

Source: [Image Classification on STL-10 (Donor/Receiver Accuracy Delta)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta>)

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

Data updated: 2026-04-07T06:47:40.408Z

Evaluation of Image Classification performance on the STL-10 dataset, focusing on the measured accuracy changes (deltas) between specified Donor and Receiver model configurations.

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 | Image Classification |
| Dataset (including any stated split) | STL-10 |
| Metric | Donor Best Top-1 Accuracy Delta |
| 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

- [Donor Best Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Donor%20Best%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Donor Worst Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Donor%20Worst%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Donor Mean Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Donor%20Mean%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Donor Positive Rate (%)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Donor%20Positive%20Rate%20(%25)>): Higher is better; unit: PERCENT.

- [Receiver Best Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Receiver%20Best%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Receiver Worst Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Receiver%20Worst%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Receiver Mean Top-1 Accuracy Delta](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Receiver%20Mean%20Top-1%20Accuracy%20Delta>): Higher is better; unit: SCALAR.

- [Receiver Positive Rate (%)](<https://www.sota2.com/research/sota/image-classification-on-stl-10-donor-receiver-accuracy-delta.md?metric=Receiver%20Positive%20Rate%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Donor Best Top-1 Accuracy Delta | Result date | Report paper |
| --- | --- | --- | --- |
| Quantization Vector Patching | 23.79 | Not recorded | 69d48f9f7d0172140ec743b3 |

### Quantization Vector Patching

Donor Best Top-1 Accuracy Delta: 23.79. Result ID: 69d4a88b47f34ce924bbe1ee.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f9f7d0172140ec743b3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f9f7d0172140ec743b3.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Protocol":"Optimized quantization vector scaling","Baseline":"Relative to vanilla PTQ"}. This record does not assert independent reproduction.

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