HyperAI초신경

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

한국어

HyperAI초신경

Prompt Engineering On Imagenet S

평가 지표

Top-1 accuracy %

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Top-1 accuracy %	Paper Title	Repository
HPT++	49.28	HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
CoCoOp	48.75	Conditional Prompt Learning for Vision-Language Models
MMRL	49.17	MMRL: Multi-Modal Representation Learning for Vision-Language Models
CoPrompt	49.43	Consistency-guided Prompt Learning for Vision-Language Models
POMP	49.8	Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
MaPLe	49.15	MaPLe: Multi-modal Prompt Learning
CLIP	46.15	Learning Transferable Visual Models From Natural Language Supervision
PromptSRC	49.55	Self-regulating Prompts: Foundational Model Adaptation without Forgetting
HPT	49.36	Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

0 of 9 row(s) selected.