# Image Classification on Tiny-ImageNet (Acc, ECE, PathSens-logit, hidden)

Source: [Image Classification on Tiny-ImageNet (Acc, ECE, PathSens-logit, hidden)](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-acc-ece-pathsens-logit-hidden>)

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

Data updated: 2026-05-12T08:52:02.520Z

Evaluation of Image Classification performance on the Tiny-ImageNet dataset, reporting Accuracy (Acc), Expected Calibration Error (ECE), Path Sensitivity (PathSens-logit), and an internal metric (hidden).

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) | Tiny-ImageNet |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-acc-ece-pathsens-logit-hidden.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Expected Calibration Error](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-acc-ece-pathsens-logit-hidden.md?metric=Expected%20Calibration%20Error>): Lower is better; unit: SCALAR.

- [PathSens-logit](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-acc-ece-pathsens-logit-hidden.md?metric=PathSens-logit>): Higher is better; unit: SCALAR.

- [Hidden Metric](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-acc-ece-pathsens-logit-hidden.md?metric=Hidden%20Metric>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Full field-aware | 11.8 | Not recorded | 6a02b42ddbc836b87d824792 |
| Task | 9.7 | Not recorded | 6a02b42ddbc836b87d824792 |

### Full field-aware

Accuracy: 11.8. Result ID: 6a02ea1e47f34ce924e5c831.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42ddbc836b87d824792.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b42ddbc836b87d824792.md>)

Recorded evaluation configuration: {"Setting":"Tiny-ImageNet reveal","Comparison":"Full field-aware"}. This record does not assert independent reproduction.

### Task

Accuracy: 9.7. Result ID: 6a02ea1e47f34ce924e5c830.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b42ddbc836b87d824792.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64aa1e209131cea05fc7.md>)

Recorded evaluation configuration: {"Setting":"Tiny-ImageNet reveal","Comparison":"Task"}. This record does not assert independent reproduction.

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