# Image Classification on Average (Flowers102, OxfordPets, VOC2007) (test)

Source: [Image Classification on Average (Flowers102, OxfordPets, VOC2007) (test)](<https://www.sota2.com/research/sota/image-classification-on-average-flowers102-oxfordpets-voc2007-test>)

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

Data updated: 2026-02-26T06:07:04.806Z

Evaluation of Image Classification performance averaged across the test splits of the Flowers102, OxfordPets, and VOC2007 datasets.

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) | Average (Flowers102, OxfordPets, VOC2007) (test) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-average-flowers102-oxfordpets-voc2007-test.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-average-flowers102-oxfordpets-voc2007-test.md?metric=Top-5%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MONA | 94.0413 | Not recorded | 68fa74a51e209131cea62e8b |
| ADAPTER | 93.9894 | Not recorded | 68fa74a51e209131cea62e8b |
| LORAND | 93.8591 | Not recorded | 68fa74a51e209131cea62e8b |
| ADAPTFORMER | 93.7023 | Not recorded | 68fa74a51e209131cea62e8b |
| BITFIT | 93.5061 | Not recorded | 68fa74a51e209131cea62e8b |
| LORA | 93.4653 | Not recorded | 68fa74a51e209131cea62e8b |
| NORMTUNING | 93.4266 | Not recorded | 68fa74a51e209131cea62e8b |
| PARTIAL-1 | 93.3292 | Not recorded | 68fa74a51e209131cea62e8b |
| FIXED | 92.8463 | Not recorded | 68fa74a51e209131cea62e8b |
| FULL | 92.7876 | Not recorded | 68fa74a51e209131cea62e8b |

### MONA

Top-1 Accuracy: 94.0413. Result ID: 699364093a6c31484915969a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Implementation](<https://github.com/Leiyi-Hu/mona>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### ADAPTER

Top-1 Accuracy: 93.9894. Result ID: 699364093a6c314849159696.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

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

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### LORAND

Top-1 Accuracy: 93.8591. Result ID: 699364093a6c314849159699.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### ADAPTFORMER

Top-1 Accuracy: 93.7023. Result ID: 699364093a6c314849159698.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b5b4.md>)

[Implementation](<https://github.com/ShoufaChen/AdaptFormer>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### BITFIT

Top-1 Accuracy: 93.5061. Result ID: 699364093a6c314849159693.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39632.md>)

[Implementation](<https://www.github.com/benzakenelad/BitFit>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### LORA

Top-1 Accuracy: 93.4653. Result ID: 699364093a6c314849159697.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### NORMTUNING

Top-1 Accuracy: 93.4266. Result ID: 699364093a6c314849159694.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fff1e209131cea48707.md>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### PARTIAL-1

Top-1 Accuracy: 93.3292. Result ID: 699364093a6c314849159695.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa619d1e209131ce9f52a3.md>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### FIXED

Top-1 Accuracy: 92.8463. Result ID: 699364093a6c314849159692.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

### FULL

Top-1 Accuracy: 92.7876. Result ID: 699364093a6c314849159691.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62e8b.md>)

Recorded evaluation configuration: {"Pre-trained Model":"Swin-L"}. This record does not assert independent reproduction.

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