# Image Classification on ImageNet-1K (val) (Top-1, Top-5, Delta dense)

Source: [Image Classification on ImageNet-1K (val) (Top-1, Top-5, Delta dense)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-top-5-delta-dense>)

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

Data updated: 2026-07-01T08:21:35.576Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting Top-1 Accuracy, Top-5 Accuracy, and Delta dense.

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-1K (val) |
| Metric | Top-1 Acc |
| 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

- [Top-1 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-top-5-delta-dense.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

- [Delta dense](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-top-5-delta-dense.md?metric=Delta%20dense>): Higher is better; unit: SCALAR.

- [Top-5 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-top-5-delta-dense.md?metric=Top-5%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| REDI with incoming attention mass | 84.706 | Not recorded | 6a449f15e0224bd4f499319f |
| Dense baseline | 83.514 | Not recorded | 6a449f15e0224bd4f499319f |
| Incoming attention mass | 82.634 | Not recorded | 6a449f15e0224bd4f499319f |
| Supervised TFIDFgt | 81.796 | Not recorded | 6a449f15e0224bd4f499319f |

### REDI with incoming attention mass

Top-1 Acc: 84.706. Result ID: 6a44ce0e73d097d845bf4a99.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f499319f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f499319f.md>)

Recorded evaluation configuration: {"Tokens":"107","Backbone":"DINOv3 ViT-B/16"}. This record does not assert independent reproduction.

### Dense baseline

Top-1 Acc: 83.514. Result ID: 6a44ce0e73d097d845bf4a96.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f499319f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a931e209131cea83fc5.md>)

Recorded evaluation configuration: {"Tokens":"201","Backbone":"DINOv3 ViT-B/16"}. This record does not assert independent reproduction.

### Incoming attention mass

Top-1 Acc: 82.634. Result ID: 6a44ce0e73d097d845bf4a98.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f499319f.md>)

Recorded evaluation configuration: {"Tokens":"107","Backbone":"DINOv3 ViT-B/16"}. This record does not assert independent reproduction.

### Supervised TFIDFgt

Top-1 Acc: 81.796. Result ID: 6a44ce0e73d097d845bf4a97.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f499319f.md>)

Recorded evaluation configuration: {"Tokens":"107","Backbone":"DINOv3 ViT-B/16"}. This record does not assert independent reproduction.

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