# Generalized Category Discovery on Tiny-ImageNet (session-averaged)

Source: [Generalized Category Discovery on Tiny-ImageNet (session-averaged)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-tiny-imagenet-session-averaged>)

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

Data updated: 2026-07-07T11:23:35.716Z

Evaluation of Generalized Category Discovery performance on the session-averaged results derived from the Tiny-ImageNet dataset, reporting metrics for all, old, and new categories.

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 | Generalized Category Discovery |
| Dataset (including any stated split) | Tiny-ImageNet (session-averaged) |
| Metric | Accuracy (All Categories) |
| 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 (All Categories)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-tiny-imagenet-session-averaged.md?metric=Accuracy%20(All%20Categories)>): Higher is better; unit: PERCENT.

- [Accuracy (Old Categories)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-tiny-imagenet-session-averaged.md?metric=Accuracy%20(Old%20Categories)>): Higher is better; unit: PERCENT.

- [Accuracy (New Categories)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-tiny-imagenet-session-averaged.md?metric=Accuracy%20(New%20Categories)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (All Categories) | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 68.4 | Not recorded | 6a4c884085dba69fef8b2deb |
| MCMI | 59.5 | Not recorded | 6a4c884085dba69fef8b2deb |

### Ours

Accuracy (All Categories): 68.4. Result ID: 6a4ce1a660b88bb339cb7ed1.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c884085dba69fef8b2deb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c884085dba69fef8b2deb.md>)

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

### MCMI

Accuracy (All Categories): 59.5. Result ID: 6a4ce1a660b88bb339cb7ed0.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c884085dba69fef8b2deb.md>)

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.