Codesota · Models · GLIPv2-H (fine-tuned)2 results · 2 benchmarks
Model card
GLIPv2-H (fine-tuned).
unknown
§ 02 · Benchmarks
Every benchmark GLIPv2-H (fine-tuned) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | COCO | Computer Vision · Object Detection | map | 62.4% | #5 | — | source ↗ |
| 02 | VQA v2.0 | Multimodal · Visual Question Answering | accuracy | 74.8% | #14 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where GLIPv2-H (fine-tuned) actually performs.
§ 04 · Papers
1 paper with results for GLIPv2-H (fine-tuned).
- 2022-06-12· 2 results
GLIPv2: Unifying Localization and Vision-Language Understanding
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
2
results
0 of 2 rows marked verified.