# Generalized Category Discovery on ImageNet-1K (test)

Source: [Generalized Category Discovery on ImageNet-1K (test)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-imagenet-1k-test>)

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

Data updated: 2026-02-26T05:34:07.343Z

Evaluation of Generalized Category Discovery performance on the test split of the ImageNet-1K dataset, reporting metrics for All, Known, and Novel 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) | ImageNet-1K (test) |
| Metric | Accuracy (All) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-imagenet-1k-test.md?metric=Accuracy%20(All)>): Higher is better; unit: PERCENT.

- [Accuracy (Known)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-imagenet-1k-test.md?metric=Accuracy%20(Known)>): Higher is better; unit: PERCENT.

- [Accuracy (Novel)](<https://www.sota2.com/research/sota/generalized-category-discovery-on-imagenet-1k-test.md?metric=Accuracy%20(Novel)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (All) | Result date | Report paper |
| --- | --- | --- | --- |
| FlipClass | 59.2 | Not recorded | 68fa75591e209131cea675df |
| SimGCD | 57.1 | Not recorded | 68fa75591e209131cea675df |
| GCD | 52.5 | Not recorded | 68fa75591e209131cea675df |

### FlipClass

Accuracy (All): 59.2. Result ID: 69939c883a6c3148491740a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75591e209131cea675df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75591e209131cea675df.md>)

Recorded evaluation configuration: {"Pretraining":"DINO"}. This record does not assert independent reproduction.

### SimGCD

Accuracy (All): 57.1. Result ID: 69939c883a6c3148491740a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75591e209131cea675df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71741e209131cea51542.md>)

[Implementation](<https://github.com/CVMI-Lab/SimGCD>)

Recorded evaluation configuration: {"Pretraining":"DINO"}. This record does not assert independent reproduction.

### GCD

Accuracy (All): 52.5. Result ID: 69939c883a6c3148491740a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75591e209131cea675df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd91e209131cea36416.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/gcd>)

Recorded evaluation configuration: {"Pretraining":"DINO"}. This record does not assert independent reproduction.

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