# Image Classification on VTAB KITTI Closest Vehicle Distance

Source: [Image Classification on VTAB KITTI Closest Vehicle Distance](<https://www.sota2.com/research/sota/image-classification-on-vtab-kitti-closest-vehicle-distance>)

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

Data updated: 2026-02-26T05:30:17.149Z

Evaluation of Image Classification performance using the VTAB subset focused on determining the closest vehicle distance within the KITTI dataset.

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) | VTAB KITTI Closest Vehicle Distance |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-vtab-kitti-closest-vehicle-distance.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Text2Concept | 18 | Not recorded | 68fa76ba1e209131cea6ec0b |
| Standard CLIP | 17 | Not recorded | 68fa76ba1e209131cea6ec0b |
| B-cosified RN-50 CLIP | 17 | Not recorded | 68fa76ba1e209131cea6ec0b |
| B-cosified RN-50 CLIP | 17 | Not recorded | 68fa76ba1e209131cea6ec0b |
| B-cosified RN-50 CLIP | 12 | Not recorded | 68fa76ba1e209131cea6ec0b |
| B-cosified RN-50 CLIP | 11 | Not recorded | 68fa76ba1e209131cea6ec0b |

### Text2Concept

Accuracy: 18. Result ID: 69944d193a6c3148491c5b99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f471e209131cea44b38.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### Standard CLIP

Accuracy: 17. Result ID: 69944d193a6c3148491c5b98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### B-cosified RN-50 CLIP

Accuracy: 17. Result ID: 69944d193a6c3148491c5b9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Implementation](<https://github.com/shrebox/B-cosification>)

Recorded evaluation configuration: {"Pre-training Dataset":"CC3M \[47\]","Learning Scheduler":"Cosine","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### B-cosified RN-50 CLIP

Accuracy: 17. Result ID: 69944d193a6c3148491c5b9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Implementation](<https://github.com/shrebox/B-cosification>)

Recorded evaluation configuration: {"Pre-training Dataset":"CC3M \[47\]","Learning Scheduler":"Cyclic","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### B-cosified RN-50 CLIP

Accuracy: 12. Result ID: 69944d193a6c3148491c5b9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Implementation](<https://github.com/shrebox/B-cosification>)

Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet \[16\]","Learning Scheduler":"Cosine","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### B-cosified RN-50 CLIP

Accuracy: 11. Result ID: 69944d193a6c3148491c5b9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ba1e209131cea6ec0b.md>)

[Implementation](<https://github.com/shrebox/B-cosification>)

Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet \[16\]","Learning Scheduler":"Cyclic","Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

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