# Image Classification on Inst. CIFAR100 (test)

Source: [Image Classification on Inst. CIFAR100 (test)](<https://www.sota2.com/research/sota/image-classification-on-inst-cifar100-test>)

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

Data updated: 2026-02-26T05:34:32.217Z

Evaluation of Image Classification performance on the Inst. CIFAR100 test set, reporting accuracy under perturbation levels defined by eta=0.2, eta=0.4, and eta=0.6.

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) | Inst. CIFAR100 (test) |
| Metric | Accuracy (eta=0.2) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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 (eta=0.2)](<https://www.sota2.com/research/sota/image-classification-on-inst-cifar100-test.md?metric=Accuracy%20(eta%3D0.2)>): Higher is better; unit: PERCENT.

- [Accuracy (eta=0.4)](<https://www.sota2.com/research/sota/image-classification-on-inst-cifar100-test.md?metric=Accuracy%20(eta%3D0.4)>): Higher is better; unit: PERCENT.

- [Accuracy (eta=0.6)](<https://www.sota2.com/research/sota/image-classification-on-inst-cifar100-test.md?metric=Accuracy%20(eta%3D0.6)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (eta=0.2) | Result date | Report paper |
| --- | --- | --- | --- |
| CAL | 69.11 | Not recorded | 68fa69991e209131cea22f22 |
| CORES^2 | 66.47 | Not recorded | 68fa69991e209131cea22f22 |
| Peer Loss | 61.16 | Not recorded | 68fa69991e209131cea22f22 |
| Forward T | 58.19 | Not recorded | 68fa69991e209131cea22f22 |
| Reweight-R | 58 | Not recorded | 68fa69991e209131cea22f22 |
| LDMI | 57.9 | Not recorded | 68fa69991e209131cea22f22 |
| CE (Standard) | 57.79 | Not recorded | 68fa69991e209131cea22f22 |
| L\_q | 57.03 | Not recorded | 68fa69991e209131cea22f22 |
| JoCoR | 43.66 | Not recorded | 68fa69991e209131cea22f22 |
| Co-teaching | 43.3 | Not recorded | 68fa69991e209131cea22f22 |
| Co-teaching+ | 41.71 | Not recorded | 68fa69991e209131cea22f22 |

### CAL

Accuracy (eta=0.2): 69.11. Result ID: 698dbf388b517eb433237bd7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Implementation](<https://github.com/UCSC-REAL/CAL>)

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

### CORES^2

Accuracy (eta=0.2): 66.47. Result ID: 698dbf388b517eb433237bd6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698f1e209131cea22a5b.md>)

[Implementation](<https://github.com/UCSC-REAL/cores>)

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

### Peer Loss

Accuracy (eta=0.2): 61.16. Result ID: 698dbf388b517eb433237bd5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68261e209131cea1a45a.md>)

[Implementation](<https://github.com/gohsyi/PeerLoss>)

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

### Forward T

Accuracy (eta=0.2): 58.19. Result ID: 698dbf388b517eb433237bce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63321e209131ce9fd4c8.md>)

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

### Reweight-R

Accuracy (eta=0.2): 58. Result ID: 698dbf388b517eb433237bd4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66d21e209131cea129ce.md>)

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

### LDMI

Accuracy (eta=0.2): 57.9. Result ID: 698dbf388b517eb433237bcf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

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

### CE (Standard)

Accuracy (eta=0.2): 57.79. Result ID: 698dbf388b517eb433237bcd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

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

### L\_q

Accuracy (eta=0.2): 57.03. Result ID: 698dbf388b517eb433237bd0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651f1e209131cea088eb.md>)

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

### JoCoR

Accuracy (eta=0.2): 43.66. Result ID: 698dbf388b517eb433237bd3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164c7.md>)

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

### Co-teaching

Accuracy (eta=0.2): 43.3. Result ID: 698dbf388b517eb433237bd1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64fe1e209131cea07aa4.md>)

[Implementation](<https://github.com/bhanML/Co-teaching>)

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

### Co-teaching+

Accuracy (eta=0.2): 41.71. Result ID: 698dbf388b517eb433237bd2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69991e209131cea22f22.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.
