# Multimodal Food Classification on Food101 90% missing rate (test)

Source: [Multimodal Food Classification on Food101 90% missing rate (test)](<https://www.sota2.com/research/sota/multimodal-food-classification-on-food101-90-percent-missing-rate-test>)

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

Data updated: 2026-05-26T09:18:42.098Z

Evaluation of Multimodal Food Classification performance on the test split of the Food101 dataset under a 90% missing data rate condition.

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 | Multimodal Food Classification |
| Dataset (including any stated split) | Food101 90% missing rate (test) |
| Metric | Text Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Text Accuracy](<https://www.sota2.com/research/sota/multimodal-food-classification-on-food101-90-percent-missing-rate-test.md?metric=Text%20Accuracy>): Higher is better; unit: PERCENT.

- [Image Accuracy](<https://www.sota2.com/research/sota/multimodal-food-classification-on-food101-90-percent-missing-rate-test.md?metric=Image%20Accuracy>): Higher is better; unit: PERCENT.

- [Both Accuracy](<https://www.sota2.com/research/sota/multimodal-food-classification-on-food101-90-percent-missing-rate-test.md?metric=Both%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/multimodal-food-classification-on-food101-90-percent-missing-rate-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Text Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AOEPT | 77.47 | Not recorded | 6a15290fdbd7150506f7de56 |
| RAGPT | 76.62 | Not recorded | 6a15290fdbd7150506f7de56 |
| SyP | 76.33 | Not recorded | 6a15290fdbd7150506f7de56 |
| DCP | 75.26 | Not recorded | 6a15290fdbd7150506f7de56 |
| MAPs | 73.16 | Not recorded | 6a15290fdbd7150506f7de56 |
| MemPrompt | 73.02 | Not recorded | 6a15290fdbd7150506f7de56 |
| LB (CLIP) | 67.22 | Not recorded | 6a15290fdbd7150506f7de56 |

### AOEPT

Text Accuracy: 77.47. Result ID: 6a156543fbc373592c0d167f.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### RAGPT

Text Accuracy: 76.62. Result ID: 6a156543fbc373592c0d167c.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79711e209131cea7da5a.md>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### SyP

Text Accuracy: 76.33. Result ID: 6a156543fbc373592c0d167e.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fa1e209131cea8064d.md>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### DCP

Text Accuracy: 75.26. Result ID: 6a156543fbc373592c0d167b.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75531e209131cea67321.md>)

[Implementation](<https://github.com/hulianyuyy/Deep_Correlated_Prompting>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### MAPs

Text Accuracy: 73.16. Result ID: 6a156543fbc373592c0d167a.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb31e209131cea418da.md>)

[Implementation](<https://github.com/YiLunLee/missing_aware_prompts>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### MemPrompt

Text Accuracy: 73.02. Result ID: 6a156543fbc373592c0d167d.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

### LB (CLIP)

Text Accuracy: 67.22. Result ID: 6a156543fbc373592c0d1679.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de56.md>)

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

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

Recorded evaluation configuration: {"Backbone":"CLIP ViT-B/16","Missing Rate":"90%"}. This record does not assert independent reproduction.

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