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

Zero Shot Transfer Image Classification On 4

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
BASIC (Lion)96.8--
CoCa96.5CoCa: Contrastive Captioners are Image-Text Foundation Models
LiT ViT-e96.1PaLI: A Jointly-Scaled Multilingual Language-Image Model
LiT-22B96.0Scaling Vision Transformers to 22 Billion Parameters
BASIC95.7Combined Scaling for Zero-shot Transfer Learning-
EVA-CLIP-18B95.7EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
EVA-CLIP-E/14+94.5EVA-CLIP: Improved Training Techniques for CLIP at Scale
LiT-tuning93.9LiT: Zero-Shot Transfer with Locked-image text Tuning
ALIGN92.2Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
CLIP88.9Learning Transferable Visual Models From Natural Language Supervision
AltCLIP87.2AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
PaLI81.97PaLI: A Jointly-Scaled Multilingual Language-Image Model
0 of 12 row(s) selected.
Zero Shot Transfer Image Classification On 4 | SOTA | HyperAI超神经