Object Retrieval on SCLARO
51.86Top-1 AccuracyScenarioCLIP
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ScenarioCLIPmode=Zero-shot, pretraining=In-domain (SCLARO), retrieval_type=image→text2025.11 | 51.86 | 64.43 | 68.3 | |
| ScenarioCLIP w/o KDmode=Zero-shot, pretraining=In-domain (SCLARO), retrieval_type=image→text2025.11 | 51.26 | 64.37 | 68.32 | |
| PyramidCLIPmode=Zero-shot, pretraining=In-domain (SCLARO), retrieval_type=image→text2025.11 | 37.67 | 59.58 | 65.92 | |
| FineCLIPmode=Zero-shot, pretraining=released weights (prompt-only), retrieval_type=image→text2025.11 | 7.76 | 20.11 | 26.88 | |
| CLIPmode=Zero-shot, pretraining=released weights (prompt-only), retrieval_type=image→text2025.11 | 3.77 | 12.35 | 18.39 | |
| SLIPmode=Zero-shot, pretraining=released weights (prompt-only), retrieval_type=image→text2025.11 | 2.96 | 9.6 | 14.22 | |
| TripletCLIPmode=Zero-shot, pretraining=released weights (prompt-only), retrieval_type=image→text2025.11 | 0.53 | 2.21 | 3.84 |