# Image Classification on ImageNet (val) (Original and R-CLR Accuracy)

Source: [Image Classification on ImageNet (val) (Original and R-CLR Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-original-and-r-clr-accuracy>)

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

Data updated: 2026-02-26T05:54:20.679Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting Original Accuracy and R-CLR Accuracy.

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) | ImageNet (val) |
| Metric | Original 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

- [Original Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-original-and-r-clr-accuracy.md?metric=Original%20Accuracy>): Higher is better; unit: PERCENT.

- [R-CLR Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-original-and-r-clr-accuracy.md?metric=R-CLR%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Original Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Taylor Pruning | 76.43 | Not recorded | 68fa69e51e209131cea24a5d |
| Taylor Pruning | 75.48 | Not recorded | 68fa69e51e209131cea24a5d |
| Taylor Pruning | 74.5 | Not recorded | 68fa69e51e209131cea24a5d |

### Taylor Pruning

Original Accuracy: 76.43. Result ID: 698def95ffc3901de099a612.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e51e209131cea24a5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f11e209131cea0d448.md>)

Recorded evaluation configuration: {"Model":"ResNet-50 91%","Params ↓ %":"11.4","FLOPs ↓ %":"20.0"}. This record does not assert independent reproduction.

### Taylor Pruning

Original Accuracy: 75.48. Result ID: 698def95ffc3901de099a610.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e51e209131cea24a5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f11e209131cea0d448.md>)

Recorded evaluation configuration: {"Model":"ResNet-50 81%","Params ↓ %":"30.1","FLOPs ↓ %":"35.0"}. This record does not assert independent reproduction.

### Taylor Pruning

Original Accuracy: 74.5. Result ID: 698def95ffc3901de099a60e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69e51e209131cea24a5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f11e209131cea0d448.md>)

Recorded evaluation configuration: {"Model":"ResNet-50 72%","Params ↓ %":"44.5","FLOPs ↓ %":"45.0"}. This record does not assert independent reproduction.

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