Open Vocabulary Attribute Detection On Ovad 1
평가 지표
mean average precision
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mean average precision | Paper Title | Repository |
|---|---|---|---|
| X-VLM | 28.0 | Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts | |
| CLIP VIT-B16 | 16.6 | Learning Transferable Visual Models From Natural Language Supervision | |
| BLIP | 24.3 | BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation | |
| Open CLIP ViT-B32 | 17.0 | Reproducible scaling laws for contrastive language-image learning | |
| OVAD-Baseline-Box | 21.4 | Open-vocabulary Attribute Detection | |
| BLIP 2 (pretrained) | 25.5 | BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models | |
| ALBEF | 21.0 | Align before Fuse: Vision and Language Representation Learning with Momentum Distillation |
0 of 7 row(s) selected.