Open Vocabulary Object Detection On Mscoco
Metrics
AP 0.5
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AP 0.5 |
|---|---|
| exploiting-unlabeled-data-with-vision-and | 34.4 |
| cora-adapting-clip-for-open-vocabulary | 41.7 |
| lp-ovod-open-vocabulary-object-detection-by | 40.5 |
| ov-dquo-open-vocabulary-detr-with-denoising | 39.2 |
| retrieval-augmented-open-vocabulary-object | 41.3 |
| object-aware-distillation-pyramid-for-open | 30.0 |
| enhancing-novel-object-detection-via | 50.3 |
| contrastive-feature-masking-open-vocabulary | 34.1 |
| detecting-twenty-thousand-classes-using-image | 27.8 |
| ov-dquo-open-vocabulary-detr-with-denoising | 45.6 |
| detect-every-thing-with-few-examples | 50 |
| aligning-bag-of-regions-for-open-vocabulary | 42.7 |
| regionclip-region-based-language-image | 31.4 |
| object-aware-distillation-pyramid-for-open | 35.6 |
| localized-vision-language-matching-for-open | 28.6 |
| sia-ovd-shape-invariant-adapter-for-bridging | 35.5 |
| bridging-the-gap-between-object-and-image | 36.9 |
| detection-oriented-image-text-pretraining-for | 46.1 |
| open-vocabulary-detr-with-conditional | 29.4 |
| zero-shot-detection-via-vision-and-language | 27.6 |
| regionclip-region-based-language-image | 39.3 |
| sia-ovd-shape-invariant-adapter-for-bridging | 41.9 |
| open-vocabulary-object-detection-using | 22.8 |
| clipself-vision-transformer-distills-itself | 44.3 |
| clim-contrastive-language-image-mosaic-for | 36.9 |
| cora-adapting-clip-for-open-vocabulary | 43.1 |
| open-vocabulary-one-stage-detection-with | 20.3 |
| open-vocabulary-attribute-detection | 30.0 |
| open-vocabulary-object-detection-with | 32.6 |
| lp-ovod-open-vocabulary-object-detection-by | 44.9 |