HyperAI초신경

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

한국어

HyperAI초신경

Image Sentence Alignment On Valse Plurality

평가 지표

Accuracy (%)

pairwise accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy (%)	pairwise accuracy	Paper Title	Repository
ViLBERT 12-in-1	62.0	72.4	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
LXMERT	55.1	64.4	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
CLIP	-	56.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT1	-	53.1	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
ViLBERT	50.3	61.2	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
VisualBERT	46.5	45.7	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
GPT2	-	51.9	VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

0 of 7 row(s) selected.