# Face Recognition on CASIA-Face100 (100-5)

Source: [Face Recognition on CASIA-Face100 (100-5)](<https://www.sota2.com/research/sota/face-recognition-on-casia-face100-100-5>)

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

Data updated: 2026-02-26T05:34:05.958Z

Evaluation of face recognition performance on the CASIA-Face100 (100-5) dataset, reporting metrics such as Accuracy (Accr, Accf) and H-measure.

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 | Face Recognition |
| Dataset (including any stated split) | CASIA-Face100 (100-5) |
| Metric | Accuracy (Accr) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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 (Accr)](<https://www.sota2.com/research/sota/face-recognition-on-casia-face100-100-5.md?metric=Accuracy%20(Accr)>): Higher is better; unit: PERCENT.

- [H-Measure](<https://www.sota2.com/research/sota/face-recognition-on-casia-face100-100-5.md?metric=H-Measure>): Higher is better; unit: PERCENT.

- [Accuracy (Accf)](<https://www.sota2.com/research/sota/face-recognition-on-casia-face100-100-5.md?metric=Accuracy%20(Accf)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Accr) | Result date | Report paper |
| --- | --- | --- | --- |
| SCRUB-S | 71.8 | Not recorded | 68fa74251e209131cea5ff6b |
| GS-LORA | 70.5 | Not recorded | 68fa74251e209131cea5ff6b |
| Pre-train | 70.2 | Not recorded | 68fa74251e209131cea5ff6b |
| FDR | 69.5 | Not recorded | 68fa74251e209131cea5ff6b |
| MAS\* | 69.2 | Not recorded | 68fa74251e209131cea5ff6b |
| EWC\* | 68.8 | Not recorded | 68fa74251e209131cea5ff6b |
| L2\* | 67.8 | Not recorded | 68fa74251e209131cea5ff6b |
| DER | 67.4 | Not recorded | 68fa74251e209131cea5ff6b |
| LwF | 67 | Not recorded | 68fa74251e209131cea5ff6b |
| DER++ | 66.9 | Not recorded | 68fa74251e209131cea5ff6b |
| SCRUB | 65.5 | Not recorded | 68fa74251e209131cea5ff6b |
| LIRF\* | 62.6 | Not recorded | 68fa74251e209131cea5ff6b |
| Retrain | 7.3 | Not recorded | 68fa74251e209131cea5ff6b |

### SCRUB-S

Accuracy (Accr): 71.8. Result ID: 699332893a6c314849145e08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71011e209131cea4e7b9.md>)

[Implementation](<https://github.com/Meghdad92/SCRUB>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### GS-LORA

Accuracy (Accr): 70.5. Result ID: 699332893a6c314849145e0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Implementation](<https://github.com/bjzhb666/GS-LoRA>)

Recorded evaluation configuration: {"Tunable Ratio":"1.28%"}. This record does not assert independent reproduction.

### Pre-train

Accuracy (Accr): 70.2. Result ID: 699332893a6c314849145dff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

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

### FDR

Accuracy (Accr): 69.5. Result ID: 699332893a6c314849145e06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f21e209131cea0d4b7.md>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### MAS\*

Accuracy (Accr): 69.2. Result ID: 699332893a6c314849145e02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e61e209131cea073fa.md>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### EWC\*

Accuracy (Accr): 68.8. Result ID: 699332893a6c314849145e01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### L2\*

Accuracy (Accr): 67.8. Result ID: 699332893a6c314849145e00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### DER

Accuracy (Accr): 67.4. Result ID: 699332893a6c314849145e04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d3e2.md>)

[Implementation](<https://github.com/aimagelab/mammoth>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### LwF

Accuracy (Accr): 67. Result ID: 699332893a6c314849145e03.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### DER++

Accuracy (Accr): 66.9. Result ID: 699332893a6c314849145e05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d3e2.md>)

[Implementation](<https://github.com/aimagelab/mammoth>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### SCRUB

Accuracy (Accr): 65.5. Result ID: 699332893a6c314849145e07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71011e209131cea4e7b9.md>)

[Implementation](<https://github.com/Meghdad92/SCRUB>)

Recorded evaluation configuration: {"Tunable Ratio":"99.73%"}. This record does not assert independent reproduction.

### LIRF\*

Accuracy (Accr): 62.6. Result ID: 699332893a6c314849145e09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cff1e209131cea372d6.md>)

Recorded evaluation configuration: {"Tunable Ratio":"50.66%"}. This record does not assert independent reproduction.

### Retrain

Accuracy (Accr): 7.3. Result ID: 699332893a6c314849145e0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

Recorded evaluation configuration: {"Tunable Ratio":"100.00%"}. This record does not assert independent reproduction.

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