# Class-Incremental Learning on ImageNet-R B100 Inc20

Source: [Class-Incremental Learning on ImageNet-R B100 Inc20](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-b100-inc20>)

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

Data updated: 2026-06-25T07:56:17.554Z

Evaluation of model performance using Class Incremental Learning methodology on the ImageNet-R dataset configured with 100 base classes (B100) and 20 incremental steps (Inc20).

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) | ImageNet-R B100 Inc20 |
| Metric | Average Performance |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Average Performance](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-b100-inc20.md?metric=Average%20Performance>): Higher is better; unit: PERCENT.

- [Last Performance](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-b100-inc20.md?metric=Last%20Performance>): Higher is better; unit: PERCENT.

- [Average Performance B](<https://www.sota2.com/research/sota/class-incremental-learning-on-imagenet-r-b100-inc20.md?metric=Average%20Performance%20B>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Performance | Result date | Report paper |
| --- | --- | --- | --- |
| AREA | 82.83 | Not recorded | 6a17cc37dbd7150506f81475 |
| BOFA | 81.72 | Not recorded | 691aac176750be83fe5ce422 |
| RAPF | 79.61 | Not recorded | 6a17cc37dbd7150506f81475 |
| ZS-CLIP | 79.57 | Not recorded | 6a17cc37dbd7150506f81475 |
| ZS-CLIP | 79.57 | Not recorded | 691aac176750be83fe5ce422 |
| SimpleCIL | 76.84 | Not recorded | 691aac176750be83fe5ce422 |
| RAPF | 76.1 | Not recorded | 691aac176750be83fe5ce422 |
| CODA-Prompt | 73.71 | Not recorded | 6a17cc37dbd7150506f81475 |
| CODA-Prompt | 73.71 | Not recorded | 691aac176750be83fe5ce422 |
| DualPrompt | 73.22 | Not recorded | 6a17cc37dbd7150506f81475 |
| DualPrompt | 73.22 | Not recorded | 691aac176750be83fe5ce422 |
| L2P | 72.82 | Not recorded | 6a17cc37dbd7150506f81475 |
| L2P | 72.82 | Not recorded | 691aac176750be83fe5ce422 |
| CoOp | 54.2 | Not recorded | 691aac176750be83fe5ce422 |
| MG-CLIP | 50.47 | Not recorded | 6a17cc37dbd7150506f81475 |
| Finetune | 1.01 | Not recorded | 691aac176750be83fe5ce422 |

### AREA

Average Performance: 82.83. Result ID: 6a181adefbc373592c129ff9.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

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

### BOFA

Average Performance: 81.72. Result ID: 6a3cdf0ffbc373592c51d415.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### RAPF

Average Performance: 79.61. Result ID: 6a181adefbc373592c129ff7.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74331e209131cea60657.md>)

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

### ZS-CLIP

Average Performance: 79.57. Result ID: 6a181adefbc373592c129ff3.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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

### ZS-CLIP

Average Performance: 79.57. Result ID: 6a3cdf0ffbc373592c51d410.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### SimpleCIL

Average Performance: 76.84. Result ID: 6a3cdf0ffbc373592c51d40f.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74641e209131cea616e7.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### RAPF

Average Performance: 76.1. Result ID: 6a3cdf0ffbc373592c51d414.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74331e209131cea60657.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### CODA-Prompt

Average Performance: 73.71. Result ID: 6a181adefbc373592c129ff6.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42add.md>)

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

### CODA-Prompt

Average Performance: 73.71. Result ID: 6a3cdf0ffbc373592c51d413.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42add.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### DualPrompt

Average Performance: 73.22. Result ID: 6a181adefbc373592c129ff5.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38614.md>)

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

### DualPrompt

Average Performance: 73.22. Result ID: 6a3cdf0ffbc373592c51d412.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38614.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### L2P

Average Performance: 72.82. Result ID: 6a181adefbc373592c129ff4.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31ad7.md>)

[Implementation](<https://github.com/google-research/l2p>)

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

### L2P

Average Performance: 72.82. Result ID: 6a3cdf0ffbc373592c51d411.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31ad7.md>)

[Implementation](<https://github.com/google-research/l2p>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### CoOp

Average Performance: 54.2. Result ID: 6a3cdf0ffbc373592c51d40e.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8b1e209131cea3a814.md>)

[Implementation](<https://github.com/KaiyangZhou/CoOp>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

### MG-CLIP

Average Performance: 50.47. Result ID: 6a181adefbc373592c129ff8.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc37dbd7150506f81475.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f61e209131cea8046b.md>)

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

### Finetune

Average Performance: 1.01. Result ID: 6a3cdf0ffbc373592c51d40d.

[Reporting paper](<https://www.sota2.com/research/paper/691aac176750be83fe5ce422.md>)

Recorded evaluation configuration: {"exemplar-free":"true","initialization":"CLIP"}. This record does not assert independent reproduction.

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