Generalized Referring Expression Segmentation
Metrics
cIoU
gIoU
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | cIoU | gIoU |
|---|---|---|
| hdc-hierarchical-semantic-decoding-with-1 | 65.42 | 68.28 |
| locate-then-segment-a-strong-pipeline-for | 52.30 | 52.70 |
| groundhog-grounding-large-language-models-to | - | 66.70 |
| vision-language-transformer-and-query | 52.51 | 52.00 |
| cris-clip-driven-referring-image-segmentation | 55.34 | 56.27 |
| bring-adaptive-binding-prototypes-to | 65.69 | 68.79 |
| gsva-generalized-segmentation-via-multimodal | 64.05 | 68.01 |
| gsva-generalized-segmentation-via-multimodal | 63.29 | 66.47 |
| gsva-generalized-segmentation-via-multimodal | 66.38 | 70.04 |
| gres-generalized-referring-expression-1 | 62.42 | 63.60 |
| lavt-language-aware-vision-transformer-for | 57.64 | 58.40 |
| mattnet-modular-attention-network-for | 47.51 | 48.24 |