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.

#BenchmarkArea · TaskMetricValueRankDateSource
01COCOComputer Vision · Object Detectionmap62.4%#5/55source ↗
02VQA v2.0Multimodal · Visual Question Answeringaccuracy74.8%#14/16source ↗
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.

Computer Vision
1
benchmark
avg rank #5.0
Multimodal
1
benchmark
avg rank #14.0
§ 04 · Papers

1 paper with results for GLIPv2-H (fine-tuned).

  1. 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.