Object Detection on ODinW 13 datasets (test)
70.4APGLIPv2-H
Evaluation results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GLIPv2-HEvaluation Protocol=Fine-tuning, Mask Annotation Usage=true2023.04 | 70.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DetCLIPv2-LEvaluation Protocol=Fine-tuning, Mask Annotation Usage=false2023.04 | 70.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIPv2-BEvaluation Protocol=Fine-tuning, Mask Annotation Usage=true2023.04 | 69.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Lprotocol=Fine-tune, scale=Larger size/More data2022.06 | 68.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-LEvaluation Protocol=Fine-tuning, Mask Annotation Usage=false2023.04 | 68.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DetCLIPv2-TEvaluation Protocol=Fine-tuning, Mask Annotation Usage=false2023.04 | 68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIPv2-TEvaluation Protocol=Fine-tuning, Mask Annotation Usage=true2023.04 | 66.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FIBER-Bprotocol=Fine-tune, scale=Larger size/More data2022.06 | 65.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Bprotocol=Fine-tune2022.06 | 65.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-TEvaluation Protocol=Fine-tuning, Mask Annotation Usage=false2023.04 | 64.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Tprotocol=Fine-tune2022.06 | 63.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Lprotocol=Zero-shot, scale=Larger size/More data2022.06 | 52.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FIBER-Bprotocol=Zero-shot, scale=Larger size/More data2022.06 | 47 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Bprotocol=Zero-shot2022.06 | 44.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-Tprotocol=Zero-shot2022.06 | 44.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-LITEText Encoding=parallel, Zero-shot=true, Training Knowledge=Wiktionary, Evaluation Knowledge Source=S_wiki_def2022.04 | 31.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-LITEText Encoding=parallel, Zero-shot=true, Training Knowledge=Wiktionary, Evaluation Knowledge Source=S_wn_path2022.04 | 30.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-AText Encoding=sequential, Zero-shot=true2022.04 | 28.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-LITEText Encoding=parallel, Zero-shot=true, Training Knowledge=Wiktionary, Evaluation Knowledge Source=S_wn_def2022.04 | 28.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Baseline GLIPText Encoding=parallel, Zero-shot=true2022.04 | 27.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Baseline GLIPText Encoding=parallel, Zero-shot=true, Knowledge Source=S_wn_path2022.04 | 26.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| K-LITEText Encoding=parallel, Zero-shot=true, Training Knowledge=Wiktionary2022.04 | 25 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Baseline GLIPText Encoding=parallel, Zero-shot=true, Knowledge Source=S_wn_def2022.04 | 21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Baseline GLIPText Encoding=parallel, Zero-shot=true, Knowledge Source=S_wiki_def2022.04 | 18.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OpenSeeD (L)Pretrain Data=Object365, COCO, Zero-shot=true2023.03 | 15.2 | 5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OpenSeeD (T)Pretrain Data=Object365, COCO, Zero-shot=true2023.03 | 14.2 | 3.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GLIP-TPretrain Data=Object365, Zero-shot=true2023.03 | 11.4 | 1.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MDETRPretrain Data=GOLDG, REFC, Zero-shot=true2023.03 | 10.7 | 3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CP-DETR-LTune=prompt2024.12 | — | — | 80.5 | 47.9 | 60.3 | 77.5 | 79 | 90.4 | 76.4 | 77 | 68.9 | 73.4 | 81.5 | 55.9 | 81.5 | 73.1 | |
| CP-DETR-TTune=prompt2024.12 | — | — | 74.2 | 37.7 | 54.4 | 78.4 | 75.5 | 88.1 | 72 | 72.8 | 61 | 72.9 | 75.9 | 54.4 | 82.2 | 69.2 | |
| DetCLIPv2-LTune=full2024.12 | — | — | 74.4 | 44.1 | 54.7 | 80.9 | 79.9 | 90 | 74.1 | 69.4 | 61.2 | 68.1 | 80.3 | 57.1 | 81.1 | 70.4 | |
| DetCLIPv3-LTune=full2024.12 | — | — | 76.4 | 51.2 | 57.5 | 79.9 | 80.2 | 90.4 | 75.1 | 70.9 | 63.6 | 69.8 | 82.7 | 56.2 | 83.8 | 72.1 | |
| GLEE-ProTune=full2024.12 | — | — | 72.6 | 36.5 | 58.1 | 80.5 | 74.1 | 92 | 67 | 76.5 | 66.4 | 70.5 | 66.4 | 55.7 | 80.6 | 69 | |
| GLIP-LTune=full2024.12 | — | — | 69.6 | 32.6 | 56.6 | 76.4 | 79.4 | 88.1 | 67.1 | 69.4 | 65.8 | 71.6 | 75.7 | 60.3 | 83.1 | 68.9 | |
| GLIP-LTune=prompt2024.12 | — | — | 72.9 | 23 | 51.8 | 72 | 75.8 | 88.1 | 75.2 | 69.5 | 73.6 | 72.1 | 73.7 | 53.5 | 81.4 | 67.9 | |
| GLIPv2-HTune=full2024.12 | — | — | 74.4 | 36.3 | 58.7 | 77.1 | 79.3 | 88.1 | 74.3 | 73.1 | 70 | 72.2 | 72.5 | 58.3 | 81.4 | 70.4 | |
| GLIPv2-HTune=prompt2024.12 | — | — | 71.2 | 31.1 | 57.1 | 75 | 79.8 | 88.1 | 68.6 | 68.3 | 59.6 | 70.9 | 73.6 | 61.4 | 78.6 | 68 | |
| Grounding-DINO-TTune=prompt2024.12 | — | — | 71.7 | 34.2 | 53 | 75.8 | 73.4 | 88.1 | 75.6 | 74.3 | 58.7 | 68 | 73.6 | 52.3 | 81.5 | 67.7 | |
| OmDet-BTune=full2024.12 | — | — | 71.2 | 27.5 | 52.7 | 76.5 | 77.4 | 93.6 | 73.7 | 74.3 | 57.7 | 64.5 | 74.2 | 56.9 | 83.3 | 68 |