# Image Classification on CIFAR-10-LT IR=10 (test)

Source: [Image Classification on CIFAR-10-LT IR=10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test>)

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

Data updated: 2026-02-26T05:34:12.561Z

Evaluation of Image Classification performance on the test split of the CIFAR-10 Long Tail (LT) dataset under the Inherent Robustness (IR) level 10 configuration, reporting adversarial robustness metrics.

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) | CIFAR-10-LT IR=10 (test) |
| Metric | Accuracy (Clean) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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 (Clean)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(Clean)>): Higher is better; unit: PERCENT.

- [Accuracy (FGSM)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(FGSM)>): Higher is better; unit: PERCENT.

- [Accuracy (PGD)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(PGD)>): Higher is better; unit: PERCENT.

- [Accuracy (AA)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(AA)>): Higher is better; unit: PERCENT.

- [Accuracy (PGD 20)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(PGD%2020)>): Higher is better; unit: PERCENT.

- [Accuracy (PGD 100)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(PGD%20100)>): Higher is better; unit: PERCENT.

- [Accuracy (CW)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-ir-10-test.md?metric=Accuracy%20(CW)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Clean) | Result date | Report paper |
| --- | --- | --- | --- |
| TAET | 74.67 | Not recorded | 68fa77941e209131cea7419b |
| REAT | 74.56 | Not recorded | 68fa77941e209131cea7419b |
| TAET | 74.48 | Not recorded | 68fa77941e209131cea7419b |
| AT-BSL | 74.34 | Not recorded | 68fa77941e209131cea7419b |
| RoBal | 73.18 | Not recorded | 68fa77941e209131cea7419b |
| AT-BSL | 72.74 | Not recorded | 68fa77941e209131cea7419b |
| AT | 69 | Not recorded | 68fa77941e209131cea7419b |
| HE | 68.18 | Not recorded | 68fa77941e209131cea7419b |
| ADT | 68.08 | Not recorded | 68fa77941e209131cea7419b |
| TRADES | 65.77 | Not recorded | 68fa77941e209131cea7419b |
| LAS-AT | 64.04 | Not recorded | 68fa77941e209131cea7419b |
| GAIRAT | 61.07 | Not recorded | 68fa77941e209131cea7419b |
| MART | 58.33 | Not recorded | 68fa77941e209131cea7419b |
| TAET | 22.65 | Not recorded | 68fa77941e209131cea7419b |
| AT-BSL | 10 | Not recorded | 68fa77941e209131cea7419b |

### TAET

Accuracy (Clean): 74.67. Result ID: 6995459c3badfaffe63345b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Implementation](<https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### REAT

Accuracy (Clean): 74.56. Result ID: 6995459c3badfaffe63345ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5095a.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### TAET

Accuracy (Clean): 74.48. Result ID: 6995459c3badfaffe6334594.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Implementation](<https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### AT-BSL

Accuracy (Clean): 74.34. Result ID: 6995459c3badfaffe6334593.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72801e209131cea56cd7.md>)

[Implementation](<https://github.com/NISPLab/AT-BSL>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### RoBal

Accuracy (Clean): 73.18. Result ID: 6995459c3badfaffe63345a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8c1e209131cea28b65.md>)

[Implementation](<https://github.com/wutong16/Adversarial_Long-Tail>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### AT-BSL

Accuracy (Clean): 72.74. Result ID: 6995459c3badfaffe63345a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72801e209131cea56cd7.md>)

[Implementation](<https://github.com/NISPLab/AT-BSL>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### AT

Accuracy (Clean): 69. Result ID: 6995459c3badfaffe63345a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665a1e209131cea0fbae.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### HE

Accuracy (Clean): 68.18. Result ID: 6995459c3badfaffe63345ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d61e209131cea1e898.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### ADT

Accuracy (Clean): 68.08. Result ID: 6995459c3badfaffe63345ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3c3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### TRADES

Accuracy (Clean): 65.77. Result ID: 6995459c3badfaffe63345a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f71e209131cea0d897.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### LAS-AT

Accuracy (Clean): 64.04. Result ID: 6995459c3badfaffe63345ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31901.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### GAIRAT

Accuracy (Clean): 61.07. Result ID: 6995459c3badfaffe63345af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0d1e209131cea25c57.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### MART

Accuracy (Clean): 58.33. Result ID: 6995459c3badfaffe63345aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Imbalance Ratio (IR)":"10"}. This record does not assert independent reproduction.

### TAET

Accuracy (Clean): 22.65. Result ID: 6995459c3badfaffe6334596.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Implementation](<https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions>)

Recorded evaluation configuration: {"Model":"ViT-B/16"}. This record does not assert independent reproduction.

### AT-BSL

Accuracy (Clean): 10. Result ID: 6995459c3badfaffe6334595.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77941e209131cea7419b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72801e209131cea56cd7.md>)

[Implementation](<https://github.com/NISPLab/AT-BSL>)

Recorded evaluation configuration: {"Model":"ViT-B/16"}. This record does not assert independent reproduction.

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