# Abnormality classification and landmarks detection on Hyper Kvasir V3

Source: [Abnormality classification and landmarks detection on Hyper Kvasir V3](<https://www.sota2.com/research/sota/abnormality-classification-and-landmarks-detection-on-hyper-kvasir-v3>)

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

Data updated: 2026-03-25T12:56:18.819Z

Evaluation of model performance on the Hyper Kvasir V3 dataset, focusing on both abnormality classification and landmark detection tasks, measured by Accuracy, F1-score, and 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 | Abnormality classification and landmarks detection |
| Dataset (including any stated split) | Hyper Kvasir V3 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/abnormality-classification-and-landmarks-detection-on-hyper-kvasir-v3.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1-score](<https://www.sota2.com/research/sota/abnormality-classification-and-landmarks-detection-on-hyper-kvasir-v3.md?metric=F1-score>): Higher is better; unit: PERCENT.

- [MCC](<https://www.sota2.com/research/sota/abnormality-classification-and-landmarks-detection-on-hyper-kvasir-v3.md?metric=MCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HMTA | 99 | Not recorded | 69c36be70636e5bf4afc632f |
| Lire-CNN | 99 | Not recorded | 69c36be70636e5bf4afc632f |
| HLNN | 98 | Not recorded | 69c36be70636e5bf4afc632f |
| EDTDE | 93 | Not recorded | 69c36be70636e5bf4afc632f |

### HMTA

Accuracy: 99. Result ID: 69c3da6d47f34ce924ad2854.

[Reporting paper](<https://www.sota2.com/research/paper/69c36be70636e5bf4afc632f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7f9f1e209131cea9aab2.md>)

Recorded evaluation configuration: {"FPS":"20"}. This record does not assert independent reproduction.

### Lire-CNN

Accuracy: 99. Result ID: 69c3da6d47f34ce924ad2857.

[Reporting paper](<https://www.sota2.com/research/paper/69c36be70636e5bf4afc632f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36be70636e5bf4afc632f.md>)

Recorded evaluation configuration: {"FPS":"41"}. This record does not assert independent reproduction.

### HLNN

Accuracy: 98. Result ID: 69c3da6d47f34ce924ad2855.

[Reporting paper](<https://www.sota2.com/research/paper/69c36be70636e5bf4afc632f.md>)

Recorded evaluation configuration: {"FPS":"129"}. This record does not assert independent reproduction.

### EDTDE

Accuracy: 93. Result ID: 69c3da6d47f34ce924ad2856.

[Reporting paper](<https://www.sota2.com/research/paper/69c36be70636e5bf4afc632f.md>)

Recorded evaluation configuration: {"FPS":"49"}. This record does not assert independent reproduction.

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