Referring Expression Comprehension on Flickr30K Entities (test)
81.99Top-1 AccuracyCLIP-VG
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIP-VGZero-Shot=false2024.03 | 81.99 | |
| SeqTRZero-Shot=false2024.03 | 81.23 | |
| Referring TransformerBackbone=RN101, Stage=One-stage, Inference time (ms)=40(15), Pre-trained=true2021.06 | 81.18 | |
| VLTVGZero-Shot=false2024.03 | 79.84 | |
| Referring TransformerBackbone=RN50, Stage=One-stage, Inference time (ms)=37(14), Pre-trained=true2021.06 | 79.46 | |
| Referring TransformerBackbone=RN101, Stage=One-stage, Inference time (ms)=40(15), Pre-trained=false2021.06 | 78.66 | |
| Referring TransformerBackbone=RN50, Stage=One-stage, Inference time (ms)=37(14), Pre-trained=false2021.06 | 78.13 | |
| Qwen-VL + SC-TuneZero-Shot=true2024.03 | 77.49 | |
| DDPNBackbone=RN101, Stage=Two-stage2021.06 | 73.3 | |
| ReSC-LargeBackbone=DN53, Stage=One-stage, Inference time (ms)=362021.06 | 69.28 | |
| FAOABackbone=DN53, Stage=One-stage, Inference time (ms)=232021.06 | 68.71 | |
| Qwen-VLZero-Shot=true2024.03 | 64.15 | |
| CITEBackbone=RN101, Stage=Two-stage, Inference time (ms)=1962021.06 | 61.33 | |
| Similarity NetBackbone=RN101, Stage=Two-stage, Inference time (ms)=1842021.06 | 60.89 | |
| MiniGPT-v2 + SC-TuneZero-Shot=true2024.03 | 60.03 | |
| ZSGNetBackbone=RN50, Stage=One-stage2021.06 | 58.63 | |
| MiniGPT-v2Zero-Shot=true2024.03 | 55.39 |