# Image Classification on CIFAR-100, SVHN, Food-101, Air, Pet, Car

Source: [Image Classification on CIFAR-100, SVHN, Food-101, Air, Pet, Car](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car>)

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

Data updated: 2026-02-26T05:34:11.714Z

Evaluation of Image Classification performance across a custom suite of six datasets: CIFAR-100, SVHN, Food-101, Air, Pet, and Car, reporting per-dataset accuracy and the overall average.

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) | Image Datasets (CIFAR-100, SVHN, Food-101, Air, Pet, Car) |
| Metric | Accuracy (CIFAR-100) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (CIFAR-100)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(CIFAR-100)>): Higher is better; unit: PERCENT.

- [Accuracy (SVHN)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(SVHN)>): Higher is better; unit: PERCENT.

- [Accuracy (Food-101)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(Food-101)>): Higher is better; unit: PERCENT.

- [Accuracy (Air)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(Air)>): Higher is better; unit: PERCENT.

- [Accuracy (Pet)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(Pet)>): Higher is better; unit: PERCENT.

- [Accuracy (Car)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Accuracy%20(Car)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-svhn-food-101-air-pet-car.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (CIFAR-100) | Result date | Report paper |
| --- | --- | --- | --- |
| AdaptFormer | 92.03 | Not recorded | 68fa753d1e209131cea66acc |
| VPT | 91.46 | Not recorded | 68fa753d1e209131cea66acc |
| LoRA | 91.42 | Not recorded | 68fa753d1e209131cea66acc |
| DyT | 91.37 | Not recorded | 68fa753d1e209131cea66acc |
| DyT + N = 4 | 91.01 | Not recorded | 68fa753d1e209131cea66acc |
| Full tuning | 90.91 | Not recorded | 68fa753d1e209131cea66acc |
| Linear | 85.87 | Not recorded | 68fa753d1e209131cea66acc |
| Dynamic-Full | 83.43 | Not recorded | 68fa753d1e209131cea66acc |

### AdaptFormer

Accuracy (CIFAR-100): 92.03. Result ID: 699383533a6c314849167e6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

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

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

Recorded evaluation configuration: {"Params (M)":"1.19","FLOPS (G)":"17.81"}. This record does not assert independent reproduction.

### VPT

Accuracy (CIFAR-100): 91.46. Result ID: 699383533a6c314849167e6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37ae9.md>)

[Implementation](<https://www.sota2.com/github.com/kmnp/vpt>)

Recorded evaluation configuration: {"Params (M)":"0.07","FLOPS (G)":"18.32"}. This record does not assert independent reproduction.

### LoRA

Accuracy (CIFAR-100): 91.42. Result ID: 699383533a6c314849167e6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

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

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

Recorded evaluation configuration: {"Params (M)":"1.19","FLOPS (G)":"17.58"}. This record does not assert independent reproduction.

### DyT

Accuracy (CIFAR-100): 91.37. Result ID: 699383533a6c314849167e6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

[Implementation](<https://github.com/NUS-HPC-AI-Lab/Dynamic-Tuning>)

Recorded evaluation configuration: {"Params (M)":"1.19","FLOPS (G)":"12.21"}. This record does not assert independent reproduction.

### DyT + N = 4

Accuracy (CIFAR-100): 91.01. Result ID: 699383533a6c314849167e70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

[Implementation](<https://github.com/NUS-HPC-AI-Lab/Dynamic-Tuning>)

Recorded evaluation configuration: {"Params (M)":"4.80","FLOPS (G)":"12.29"}. This record does not assert independent reproduction.

### Full tuning

Accuracy (CIFAR-100): 90.91. Result ID: 699383533a6c314849167e69.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

Recorded evaluation configuration: {"Params (M)":"85.80","FLOPS (G)":"17.58"}. This record does not assert independent reproduction.

### Linear

Accuracy (CIFAR-100): 85.87. Result ID: 699383533a6c314849167e6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

Recorded evaluation configuration: {"Params (M)":"0","FLOPS (G)":"17.58"}. This record does not assert independent reproduction.

### Dynamic-Full

Accuracy (CIFAR-100): 83.43. Result ID: 699383533a6c314849167e6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753d1e209131cea66acc.md>)

Recorded evaluation configuration: {"Params (M)":"85.80","FLOPS (G)":"12.24"}. This record does not assert independent reproduction.

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