HyperAI超神经

首页算力平台文档资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Image Sentence Alignment On Valse Spatial

评估指标

Accuracy (%)

pairwise accuracy

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
GPT1	-	77.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT2	-	75.0	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
ViLBERT 12-in-1	53.4	67.7	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
CLIP	-	64.3	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
LXMERT	50.8	60.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
ViLBERT	49.9	57.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
VisualBERT	49.3	39.7	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

0 of 7 row(s) selected.

Image Sentence Alignment On Valse Spatial | SOTA | HyperAI超神经