# Object Detection on LVIS V1 (rare)

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

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

Data updated: 2026-06-17T07:52:55.106Z

Evaluation of Object Detection performance on the rare category subset of the LVIS v1 dataset, utilizing specialized metrics like Ins., Del., and Point Game scores.

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 V1 (rare) |
| Metric | Ins. |
| 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

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

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

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

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

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

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

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

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

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

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

- [A/C Ratio](<https://www.sota2.com/research/sota/object-detection-on-lvis-v1-rare.md?metric=A%2FC%20Ratio>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Ins. | Result date | Report paper |
| --- | --- | --- | --- |
| Greedy | 36.95 | Not recorded | 6a322a57d33dfb23e783ed5d |
| Greedy | 34.11 | Not recorded | 6a322a57d33dfb23e783ed5d |
| PhaseWin | 33.63 | Not recorded | 6a322a57d33dfb23e783ed5d |
| PhaseWin | 30.71 | Not recorded | 6a322a57d33dfb23e783ed5d |
| RISE | 28.08 | Not recorded | 6a322a57d33dfb23e783ed5d |
| HSIC | 24.17 | Not recorded | 6a322a57d33dfb23e783ed5d |
| ODAM | 20.09 | Not recorded | 6a322a57d33dfb23e783ed5d |
| Grad-CAM | 12.53 | Not recorded | 6a322a57d33dfb23e783ed5d |
| SSGrad-CAM++ | 12.53 | Not recorded | 6a322a57d33dfb23e783ed5d |

### Greedy

Ins.: 36.95. Result ID: 6a325254fbc373592c2fa661.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a16.md>)

[Implementation](<https://github.com/RuoyuChen10/SMDL-Attribution>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Number of regions":"100","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### Greedy

Ins.: 34.11. Result ID: 6a325254fbc373592c2fa65f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a16.md>)

[Implementation](<https://github.com/RuoyuChen10/SMDL-Attribution>)

Recorded evaluation configuration: {"Model":"Grounding DINO","Number of regions":"50","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### PhaseWin

Ins.: 33.63. Result ID: 6a325254fbc373592c2fa662.

[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","Number of regions":"100","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### PhaseWin

Ins.: 30.71. Result ID: 6a325254fbc373592c2fa660.

[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","Number of regions":"50","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### RISE

Ins.: 28.08. Result ID: 6a325254fbc373592c2fa65c.

[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","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### HSIC

Ins.: 24.17. Result ID: 6a325254fbc373592c2fa65d.

[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","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### ODAM

Ins.: 20.09. Result ID: 6a325254fbc373592c2fa65e.

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

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

### Grad-CAM

Ins.: 12.53. Result ID: 6a325254fbc373592c2fa65a.

[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","Zero-shot evaluation protocol":"true"}. This record does not assert independent reproduction.

### SSGrad-CAM++

Ins.: 12.53. Result ID: 6a325254fbc373592c2fa65b.

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

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

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