# Image Classification on Occluded-OOD-CV 40-60% occlusion 1.0

Source: [Image Classification on Occluded-OOD-CV 40-60% occlusion 1.0](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0>)

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

Data updated: 2026-02-26T06:07:15.515Z

Evaluation of Image Classification performance on the Occluded-OOD-CV dataset, specifically focusing on robustness across different factors (context, weather, texture, pose, shape) under 40% to 60% occlusion levels.

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) | Occluded-OOD-CV 40-60% occlusion 1.0 |
| Metric | Top-1 Accuracy (Combined) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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 (Combined)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Combined)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Context)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Context)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Weather)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Weather)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Texture)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Texture)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Pose)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Pose)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Shape)](<https://www.sota2.com/research/sota/image-classification-on-occluded-ood-cv-40-60-percent-occlusion-1-0.md?metric=Top-1%20Accuracy%20(Shape)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (Combined) | Result date | Report paper |
| --- | --- | --- | --- |
| UGT | 57 | Not recorded | 68fa76e61e209131cea6fc81 |
| CST | 53.9 | Not recorded | 68fa76e61e209131cea6fc81 |

### UGT

Top-1 Accuracy (Combined): 57. Result ID: 6994665e3a6c3148491cfc90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e61e209131cea6fc81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76e61e209131cea6fc81.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### CST

Top-1 Accuracy (Combined): 53.9. Result ID: 6994665e3a6c3148491cfc8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e61e209131cea6fc81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2c1e209131cea2c8a9.md>)

[Implementation](<https://github.com/Liuhong99/CST>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Pre-training":"Pretrained ImageNet","Evaluation Protocol":"Pretrained UDA model"}. This record does not assert independent reproduction.

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