# Continual Food Recognition on VFN186 Insulin

Source: [Continual Food Recognition on VFN186 Insulin](<https://www.sota2.com/research/sota/continual-food-recognition-on-vfn186-insulin>)

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

Data updated: 2026-04-01T07:02:21.216Z

Evaluation of Continual Food Recognition performance on the VFN186 Insulin dataset, reporting accuracy metrics specific to continual learning scenarios (Last task accuracy, Average 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 | Continual Food Recognition |
| Dataset (including any stated split) | VFN186 Insulin |
| Metric | Last Task Accuracy (AT) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Last Task Accuracy (AT)](<https://www.sota2.com/research/sota/continual-food-recognition-on-vfn186-insulin.md?metric=Last%20Task%20Accuracy%20(AT)>): Higher is better; unit: PERCENT.

- [Average Accuracy (A-bar)](<https://www.sota2.com/research/sota/continual-food-recognition-on-vfn186-insulin.md?metric=Average%20Accuracy%20(A-bar)>): Higher is better; unit: PERCENT.

- [Weighted Average Accuracy (wA-bar)](<https://www.sota2.com/research/sota/continual-food-recognition-on-vfn186-insulin.md?metric=Weighted%20Average%20Accuracy%20(wA-bar)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Last Task Accuracy (AT) | Result date | Report paper |
| --- | --- | --- | --- |
| DIME | 69.4 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| TUNA | 66.28 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| ACMap | 66.22 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| MOS | 65.64 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| EASE | 65.11 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| SLCA | 63.1 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| CL-LoRA | 60.57 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| InfLoRA | 51.83 | Not recorded | 69cca67e0636e5bf4afcbb32 |
| SEMA | 43.45 | Not recorded | 69cca67e0636e5bf4afcbb32 |

### DIME

Last Task Accuracy (AT): 69.4. Result ID: 69ccc2f547f34ce924b5f7bc.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### TUNA

Last Task Accuracy (AT): 66.28. Result ID: 69ccc2f547f34ce924b5f7bb.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a841e209131cea83a59.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### ACMap

Last Task Accuracy (AT): 66.22. Result ID: 69ccc2f547f34ce924b5f7b9.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77991e209131cea7442a.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### MOS

Last Task Accuracy (AT): 65.64. Result ID: 69ccc2f547f34ce924b5f7ba.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa797b1e209131cea7dbd3.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### EASE

Last Task Accuracy (AT): 65.11. Result ID: 69ccc2f547f34ce924b5f7b6.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72981e209131cea57699.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### SLCA

Last Task Accuracy (AT): 63.1. Result ID: 69ccc2f547f34ce924b5f7b4.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70c91e209131cea4d120.md>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### CL-LoRA

Last Task Accuracy (AT): 60.57. Result ID: 69ccc2f547f34ce924b5f7b8.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb1b.md>)

[Implementation](<https://github.com/JiangpengHe/CL-LoRA>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### InfLoRA

Last Task Accuracy (AT): 51.83. Result ID: 69ccc2f547f34ce924b5f7b5.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bb1e209131cea58354.md>)

[Implementation](<https://github.com/liangyanshuo/InfLoRA>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

### SEMA

Last Task Accuracy (AT): 43.45. Result ID: 69ccc2f547f34ce924b5f7b7.

[Reporting paper](<https://www.sota2.com/research/paper/69cca67e0636e5bf4afcbb32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a41e209131cea748f4.md>)

[Implementation](<https://github.com/huiyiwang01/SEMA-CL>)

Recorded evaluation configuration: {"Step-imbalance ratio (rho)":"0.01","Averaged over":"5 runs"}. This record does not assert independent reproduction.

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