HyperAIHyperAI超神経
ホームニュース論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Zero Shot Transfer Image Classification On 3

評価指標

Accuracy (Private)
Accuracy (Public)

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Accuracy (Private)
Accuracy (Public)
Paper TitleRepository
LiT-tuning78.7 66.6LiT: Zero-Shot Transfer with Locked-image text Tuning
InternVL-C77.3-InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
PaLI64.46-PaLI: A Jointly-Scaled Multilingual Language-Image Model
CoCa80.7-CoCa: Contrastive Captioners are Image-Text Foundation Models
AltCLIP68.1-AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities
LiT ViT-e80.6-PaLI: A Jointly-Scaled Multilingual Language-Image Model
ALIGN 70.1-Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
EVA-CLIP-E/14+75.7-EVA-CLIP: Improved Training Techniques for CLIP at Scale
BASIC (Lion)81.2---
EVA-CLIP-18B77.9-EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
LiT-22B80.9-Scaling Vision Transformers to 22 Billion Parameters
BASIC80.6-Combined Scaling for Zero-shot Transfer Learning-
CLIP70.1-Learning Transferable Visual Models From Natural Language Supervision
0 of 13 row(s) selected.