# Long-tailed Recognition on Places-LT Backward (test)

Source: [Long-tailed Recognition on Places-LT Backward (test)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test>)

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

Data updated: 2026-02-26T06:07:15.641Z

Evaluation of Long-tailed Recognition performance on the 'Backward' test split of the Places-LT dataset, measured using Inverse Ranking (IR) accuracy thresholds (IR 50 down to IR 2).

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 | Long-tailed Recognition |
| Dataset (including any stated split) | Places-LT Backward (test) |
| Metric | Top-1 Accuracy (IR 2) |
| 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

- [Top-1 Accuracy (IR 2)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test.md?metric=Top-1%20Accuracy%20(IR%202)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (IR 5)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test.md?metric=Top-1%20Accuracy%20(IR%205)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (IR 10)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test.md?metric=Top-1%20Accuracy%20(IR%2010)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (IR 25)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test.md?metric=Top-1%20Accuracy%20(IR%2025)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (IR 50)](<https://www.sota2.com/research/sota/long-tailed-recognition-on-places-lt-backward-test.md?metric=Top-1%20Accuracy%20(IR%2050)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (IR 2) | Result date | Report paper |
| --- | --- | --- | --- |
| SADE | 40.6 | Not recorded | 68fa6dc51e209131cea3c01a |
| RIDE | 39.6 | Not recorded | 68fa6dc51e209131cea3c01a |
| LADE | 39.2 | Not recorded | 68fa6dc51e209131cea3c01a |
| BS | 38.5 | Not recorded | 68fa6dc51e209131cea3c01a |
| LADE | 38.1 | Not recorded | 68fa6dc51e209131cea3c01a |
| MISLAS | 37.3 | Not recorded | 68fa6dc51e209131cea3c01a |
| Softmax | 28.4 | Not recorded | 68fa6dc51e209131cea3c01a |

### SADE

Top-1 Accuracy (IR 2): 40.6. Result ID: 698fdc723a6c314849fc5f14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Implementation](<https://github.com/Vanint/SADE-AgnosticLT>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

### RIDE

Top-1 Accuracy (IR 2): 39.6. Result ID: 698fdc723a6c314849fc5f13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7b1e209131cea3436b.md>)

[Implementation](<https://github.com/frank-xwang/RIDE-LongTailRecognition>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

### LADE

Top-1 Accuracy (IR 2): 39.2. Result ID: 698fdc723a6c314849fc5f12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Test Class Prior":true}. This record does not assert independent reproduction.

### BS

Top-1 Accuracy (IR 2): 38.5. Result ID: 698fdc723a6c314849fc5f0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e125.md>)

[Implementation](<https://github.com/jiawei-ren/BalancedMetaSoftmax>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

### LADE

Top-1 Accuracy (IR 2): 38.1. Result ID: 698fdc723a6c314849fc5f11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

### MISLAS

Top-1 Accuracy (IR 2): 37.3. Result ID: 698fdc723a6c314849fc5f10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea237df.md>)

[Implementation](<https://github.com/Jia-Research-Lab/MiSLAS>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

### Softmax

Top-1 Accuracy (IR 2): 28.4. Result ID: 698fdc723a6c314849fc5f0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b21e209131cea237df.md>)

[Implementation](<https://github.com/Jia-Research-Lab/MiSLAS>)

Recorded evaluation configuration: {"Test Class Prior":false}. This record does not assert independent reproduction.

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