# Class-Incremental Learning on Dissimilar Tasks (CIFAR-10, SVHN, STL-10, MNIST, Fashion-MNIST)

Source: [Class-Incremental Learning on Dissimilar Tasks (CIFAR-10, SVHN, STL-10, MNIST, Fashion-MNIST)](<https://www.sota2.com/research/sota/class-incremental-learning-on-dissimilar-tasks-cifar-10-svhn-stl-10-mnist-fashion-mnist>)

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

Data updated: 2026-02-26T05:36:03.487Z

Evaluation of Class-Incremental Learning performance across a suite of standard small image classification datasets, including CIFAR-10, SVHN, STL-10, MNIST, and Fashion-MNIST.

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 | Class-Incremental Learning |
| Dataset (including any stated split) | Dissimilar tasks (CIFAR-10, SVHN, STL-10, MNIST, Fashion-MNIST) |
| Metric | Avg Acc (Af) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Avg Acc (Af)](<https://www.sota2.com/research/sota/class-incremental-learning-on-dissimilar-tasks-cifar-10-svhn-stl-10-mnist-fashion-mnist.md?metric=Avg%20Acc%20(Af)>): Higher is better; unit: PERCENT.

- [Accuracy Avg (Aa)](<https://www.sota2.com/research/sota/class-incremental-learning-on-dissimilar-tasks-cifar-10-svhn-stl-10-mnist-fashion-mnist.md?metric=Accuracy%20Avg%20(Aa)>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/class-incremental-learning-on-dissimilar-tasks-cifar-10-svhn-stl-10-mnist-fashion-mnist.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Top-1 Acc](<https://www.sota2.com/research/sota/class-incremental-learning-on-dissimilar-tasks-cifar-10-svhn-stl-10-mnist-fashion-mnist.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Acc (Af) | Result date | Report paper |
| --- | --- | --- | --- |
| SSIL | 67 | Not recorded | 68fa6f161e209131cea43d62 |
| SSIL | 66.15 | Not recorded | 68fa6f161e209131cea43d62 |
| SSIL | 65.64 | Not recorded | 68fa6f161e209131cea43d62 |
| EEIL | 64.88 | Not recorded | 68fa6f161e209131cea43d62 |
| LUCIR | 63.64 | Not recorded | 68fa6f161e209131cea43d62 |
| FT | 63.42 | Not recorded | 68fa6f161e209131cea43d62 |
| LUCIR | 62.99 | Not recorded | 68fa6f161e209131cea43d62 |
| LUCIR | 62.42 | Not recorded | 68fa6f161e209131cea43d62 |
| EEIL | 62.04 | Not recorded | 68fa6f161e209131cea43d62 |
| EEIL | 61.73 | Not recorded | 68fa6f161e209131cea43d62 |
| FT | 61.41 | Not recorded | 68fa6f161e209131cea43d62 |
| FT | 59.6 | Not recorded | 68fa6f161e209131cea43d62 |

### SSIL

Avg Acc (Af): 67. Result ID: 699096213a6c31484901a80c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"TBBN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### SSIL

Avg Acc (Af): 66.15. Result ID: 699096213a6c31484901a80a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"BN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### SSIL

Avg Acc (Af): 65.64. Result ID: 699096213a6c31484901a80b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"CN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### EEIL

Avg Acc (Af): 64.88. Result ID: 699096213a6c31484901a806.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"TBBN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### LUCIR

Avg Acc (Af): 63.64. Result ID: 699096213a6c31484901a809.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"TBBN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### FT

Avg Acc (Af): 63.42. Result ID: 699096213a6c31484901a803.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"TBBN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### LUCIR

Avg Acc (Af): 62.99. Result ID: 699096213a6c31484901a808.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"CN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### LUCIR

Avg Acc (Af): 62.42. Result ID: 699096213a6c31484901a807.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"BN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### EEIL

Avg Acc (Af): 62.04. Result ID: 699096213a6c31484901a804.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"BN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### EEIL

Avg Acc (Af): 61.73. Result ID: 699096213a6c31484901a805.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"CN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### FT

Avg Acc (Af): 61.41. Result ID: 699096213a6c31484901a802.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"CN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### FT

Avg Acc (Af): 59.6. Result ID: 699096213a6c31484901a801.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f161e209131cea43d62.md>)

Recorded evaluation configuration: {"Normalization":"BN","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

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