# Object Detection on LVIS rare (misclassified samples) V1 (val)

Source: [Object Detection on LVIS rare (misclassified samples) V1 (val)](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val>)

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

Data updated: 2026-06-17T07:52:54.975Z

Evaluation of Object Detection performance on a specific subset of the LVIS V1 validation set, focusing on rare categories identified by misclassified samples. Metrics include Ins., ESR, and A-C ratio.

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 | Object Detection |
| Dataset (including any stated split) | LVIS rare (misclassified samples) V1 (val) |
| Metric | Ins. AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Ins. AP](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=Ins.%20AP>): Higher is better; unit: PERCENT.

- [Ins. AP (Class)](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=Ins.%20AP%20(Class)>): Higher is better; unit: PERCENT.

- [Average High Score](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=Average%20High%20Score>): Higher is better; unit: PERCENT.

- [ESR](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=ESR>): Lower is better; unit: PERCENT.

- [MEC Average](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=MEC%20Average>): Higher is better; unit: SCALAR.

- [A-C Ratio](<https://www.sota2.com/research/sota/object-detection-on-lvis-rare-misclassified-samples-v1-val.md?metric=A-C%20Ratio>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Ins. AP | Result date | Report paper |
| --- | --- | --- | --- |
| Greedy-100 | 17.76 | Not recorded | 6a322a57d33dfb23e783ed5d |
| PhaseWin-100 | 14.75 | Not recorded | 6a322a57d33dfb23e783ed5d |
| PhaseWin-50 | 13.94 | Not recorded | 6a322a57d33dfb23e783ed5d |
| RISE | 12.45 | Not recorded | 6a322a57d33dfb23e783ed5d |
| HSIC | 9.63 | Not recorded | 6a322a57d33dfb23e783ed5d |
| ODAM | 5.75 | Not recorded | 6a322a57d33dfb23e783ed5d |
| SSGrad-CAM++ | 5.74 | Not recorded | 6a322a57d33dfb23e783ed5d |
| Grad-CAM | 5.03 | Not recorded | 6a322a57d33dfb23e783ed5d |

### Greedy-100

Ins. AP: 17.76. Result ID: 6a325254fbc373592c2fa63e.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77c11e209131cea751d3.md>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot","Budget":"100"}. This record does not assert independent reproduction.

### PhaseWin-100

Ins. AP: 14.75. Result ID: 6a325254fbc373592c2fa640.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot","Budget":"100"}. This record does not assert independent reproduction.

### PhaseWin-50

Ins. AP: 13.94. Result ID: 6a325254fbc373592c2fa63f.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot","Budget":"50"}. This record does not assert independent reproduction.

### RISE

Ins. AP: 12.45. Result ID: 6a325254fbc373592c2fa63b.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64dc1e209131cea06cb9.md>)

[Implementation](<https://github.com/pytorch/vision>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot"}. This record does not assert independent reproduction.

### HSIC

Ins. AP: 9.63. Result ID: 6a325254fbc373592c2fa63c.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d891e209131cea3a77b.md>)

[Implementation](<https://github.com/paulnovello/HSIC-Attribution-Method>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot"}. This record does not assert independent reproduction.

### ODAM

Ins. AP: 5.75. Result ID: 6a325254fbc373592c2fa63d.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot"}. This record does not assert independent reproduction.

### SSGrad-CAM++

Ins. AP: 5.74. Result ID: 6a325254fbc373592c2fa63a.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot"}. This record does not assert independent reproduction.

### Grad-CAM

Ins. AP: 5.03. Result ID: 6a325254fbc373592c2fa639.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a57d33dfb23e783ed5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cb1e209131cea12568.md>)

[Implementation](<https://github.com/ramprs/grad-cam/>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Mode":"Zero-shot"}. This record does not assert independent reproduction.

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