HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Prompt Engineering On Imagenet V2

평가 지표

Top-1 accuracy %

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Top-1 accuracy %	Paper Title	Repository
CoCoOp	64.07	Conditional Prompt Learning for Vision-Language Models
MaPLe	64.07	MaPLe: Multi-modal Prompt Learning
POMP	63.8	-	-
CLIP	60.83	Learning Transferable Visual Models From Natural Language Supervision
HPT	65.25	Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models
MMRL	64.47	MMRL: Multi-Modal Representation Learning for Vision-Language Models
HPT++	65.31	HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
PromptSRC	64.35	Self-regulating Prompts: Foundational Model Adaptation without Forgetting

0 of 8 row(s) selected.