HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Visual Entailment On Snli Ve Test

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
OFA91.2OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Prompt Tuning90.12Prompt Tuning for Generative Multimodal Pretrained Models
CoCa87.1CoCa: Contrastive Captioners are Image-Text Foundation Models
SimVLM86.32SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
SOHO84.95Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
MAD (Single Model, Formerly CLIP-TD)80.32Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks-
UNITER (Large)78.98UNITER: UNiversal Image-TExt Representation Learning
EVE-ROI*70.47Visual Entailment: A Novel Task for Fine-Grained Image Understanding
0 of 8 row(s) selected.
Visual Entailment On Snli Ve Test | SOTA | HyperAI超神经