# Image Classification on ALL-IDB2

Source: [Image Classification on ALL-IDB2](<https://www.sota2.com/research/sota/image-classification-on-all-idb2>)

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

Data updated: 2026-05-14T07:35:15.508Z

Evaluation of Image Classification performance on the ALL-IDB2 dataset, reporting Accuracy and Matthews Correlation Coefficient (MCC).

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) | ALL-IDB2 |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-all-idb2.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [MCC](<https://www.sota2.com/research/sota/image-classification-on-all-idb2.md?metric=MCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Bayesian CNN + Augmentation | 98.65 | Not recorded | 6a0556e7dbc836b87d828ade |
| PRISM (ET+SVM+LogReg) | 98.46 | Not recorded | 6a0556e7dbc836b87d828ade |
| CNN (ResNet + GA) | 98.46 | Not recorded | 6a0556e7dbc836b87d828ade |
| Hybrid CNN Ensemble (MobileNet + ShuffleNet) | 98.46 | Not recorded | 6a0556e7dbc836b87d828ade |
| PRISM | 98.46 | Not recorded | 6a0556e7dbc836b87d828ade |
| EfficientNet-B0 | 98.08 | Not recorded | 6a0556e7dbc836b87d828ade |
| DenseNet-121 | 97.69 | Not recorded | 6a0556e7dbc836b87d828ade |
| VGG16 | 97.69 | Not recorded | 6a0556e7dbc836b87d828ade |
| Handcrafted (SIFT+SURF) | 97.22 | Not recorded | 6a0556e7dbc836b87d828ade |
| CNN (MobileNet + ResNet) | 97.18 | Not recorded | 6a0556e7dbc836b87d828ade |
| ResNet-18 | 96.54 | Not recorded | 6a0556e7dbc836b87d828ade |
| CNN (VGG + SESSA) | 96.11 | Not recorded | 6a0556e7dbc836b87d828ade |
| Handcrafted (KNN) | 95.67 | Not recorded | 6a0556e7dbc836b87d828ade |
| Swin Transformer (Swin-T) | 91.92 | Not recorded | 6a0556e7dbc836b87d828ade |
| Handcrafted (EOF+MLP) | 91.8 | Not recorded | 6a0556e7dbc836b87d828ade |
| Hybrid CNN (ResNet + GA) | 85 | Not recorded | 6a0556e7dbc836b87d828ade |

### Bayesian CNN + Augmentation

Accuracy: 98.65. Result ID: 6a057ab947f34ce924ec2203.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Bayesian CNN + Augmentation"}. This record does not assert independent reproduction.

### PRISM (ET+SVM+LogReg)

Accuracy: 98.46. Result ID: 6a057ab947f34ce924ec21fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"Multiscale Zonal Extraction + Stacking"}. This record does not assert independent reproduction.

### CNN (ResNet + GA)

Accuracy: 98.46. Result ID: 6a057ab947f34ce924ec2201.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"CNN (ResNet + GA)"}. This record does not assert independent reproduction.

### Hybrid CNN Ensemble (MobileNet + ShuffleNet)

Accuracy: 98.46. Result ID: 6a057ab947f34ce924ec2202.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Hybrid CNN Ensemble (MobileNet + ShuffleNet)"}. This record does not assert independent reproduction.

### PRISM

Accuracy: 98.46. Result ID: 6a057ab947f34ce924ec2204.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Zonal Stacking Ensemble"}. This record does not assert independent reproduction.

### EfficientNet-B0

Accuracy: 98.08. Result ID: 6a057ab947f34ce924ec21f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"CNN"}. This record does not assert independent reproduction.

### DenseNet-121

Accuracy: 97.69. Result ID: 6a057ab947f34ce924ec21f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"CNN"}. This record does not assert independent reproduction.

### VGG16

Accuracy: 97.69. Result ID: 6a057ab947f34ce924ec21f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"CNN"}. This record does not assert independent reproduction.

### Handcrafted (SIFT+SURF)

Accuracy: 97.22. Result ID: 6a057ab947f34ce924ec21fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Handcrafted (SIFT+SURF)"}. This record does not assert independent reproduction.

### CNN (MobileNet + ResNet)

Accuracy: 97.18. Result ID: 6a057ab947f34ce924ec2200.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"CNN (MobileNet + ResNet)"}. This record does not assert independent reproduction.

### ResNet-18

Accuracy: 96.54. Result ID: 6a057ab947f34ce924ec21f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"CNN"}. This record does not assert independent reproduction.

### CNN (VGG + SESSA)

Accuracy: 96.11. Result ID: 6a057ab947f34ce924ec21ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"CNN (VGG + SESSA)"}. This record does not assert independent reproduction.

### Handcrafted (KNN)

Accuracy: 95.67. Result ID: 6a057ab947f34ce924ec21fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Handcrafted (KNN)"}. This record does not assert independent reproduction.

### Swin Transformer (Swin-T)

Accuracy: 91.92. Result ID: 6a057ab947f34ce924ec21f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Computational Paradigm":"Vision Transformer (Self-Attention)"}. This record does not assert independent reproduction.

### Handcrafted (EOF+MLP)

Accuracy: 91.8. Result ID: 6a057ab947f34ce924ec21fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Handcrafted (EOF+MLP)"}. This record does not assert independent reproduction.

### Hybrid CNN (ResNet + GA)

Accuracy: 85. Result ID: 6a057ab947f34ce924ec21fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556e7dbc836b87d828ade.md>)

Recorded evaluation configuration: {"Methodology":"Hybrid CNN (ResNet + GA)"}. This record does not assert independent reproduction.

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