Papers with Code · CC BY-SA 4.0

Winoground

아카이브 평가 114건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
LLaVA-1.5-CCoT	Text Score 42.0 Image Score 35.5 Group Score 22.3	Compositional Chain-of-Thought Prompting for Large Multimodal Models 2023-11-27	코드 1
BLIP2	Text Score 42.0 Image Score 23.8 Group Score 19.0	Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10	연결 없음
IAIS large (COCO)	Text Score 41.75 Image Score 19.75 Group Score 15.50	Does Structural Attention Improve Compositional Representations in Vision-Language Models? 2022-12-03	연결 없음
NegBLIP2	Text Score 41.5 Image Score 26.0 Group Score 20.5	Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10	연결 없음
BLIP (+Graph Text, +Graph Neg)	Text Score 40.5 Image Score 25.5 Group Score 19.0	Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10	연결 없음
BLIP (+Graph Text)	Text Score 40.3 Image Score 20.5 Group Score 16.5	Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10	연결 없음
Gemini + CoCoT	Text Score 40 Image Score 32.5 Group Score 27.75	CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs 2024-01-05	코드 1
CACR base	Text Score 39.25 Image Score 17.75 Group Score 14.25	Does Structural Attention Improve Compositional Representations in Vision-Language Models? 2022-12-03	연결 없음
METER	Text Score 39.25 Image Score 15.75 Group Score 12.00	Equivariant Similarity for Vision-Language Foundation Models 2023-03-25	코드 1
OpenFlamingo	Text Score 39 Image Score 41.25 Group Score 33.25	CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs 2024-01-05	코드 1
BLIP	Text Score 39.0 Image Score 19.2 Group Score 15.0	Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10	연결 없음
GPT-4V (image-caption match answer yes/no, zero-shot)	Text Score 38.00 Image Score 38.00 Group Score 38.00	연결 없음 논문 날짜 미기재	연결 없음
UNITER large	Text Score 38.00 Image Score 14.00 Group Score 10.50	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2
VinVL	Text Score 37.75 Image Score 17.75 Group Score 14.50	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2
ViLLA large	Text Score 37.00 Image Score 13.25 Group Score 11.00	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2
BLIP (VisualGPTScore, α-tuned)	Text Score 36.5 Image Score 21.5 Group Score 16.8	Revisiting the Role of Language Priors in Vision-Language Models 2023-06-02	코드 1
BLIP 14M	Text Score 36.5 Image Score 18.5 Group Score 14.5	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
ViT-B/16 + BERT base + ViLEM	Text Score 36.5	ViLEM: Visual-Language Error Modeling for Image-Text Retrieval 2023-01-01	연결 없음
LLaVA-1.5	Text Score 36.0 Image Score 33.3 Group Score 20.1	Compositional Chain-of-Thought Prompting for Large Multimodal Models 2023-11-27	코드 1
BLIP (ITM)	Text Score 35.8 Image Score 15.8 Group Score 13.3	Revisiting the Role of Language Priors in Vision-Language Models 2023-06-02	코드 1
BLIP 129M	Text Score 35.5 Image Score 15.0 Group Score 11.7	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
ROSITA (Flickr30k)	Text Score 35.25 Image Score 15.25 Group Score 12.25	Does Structural Attention Improve Compositional Representations in Vision-Language Models? 2022-12-03	연결 없음
ViLT (ViT-B/32)	Text Score 34.75 Image Score 14.00 Group Score 9.25	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2
BLIP 129M (CapFilt/L)	Text Score 34.7 Image Score 15.2 Group Score 12.2	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
BLIP-ViT/L 129M	Text Score 34.7 Image Score 14.5 Group Score 12.2	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
Diffusion Classifier (zero-shot)	Text Score 34.00	Your Diffusion Model is Secretly a Zero-Shot Classifier 2023-03-28	코드 1 · 코드 2 · 코드 3 · 코드 4
PEVL 14M	Text Score 33.2 Image Score 15.7 Group Score 12.2	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
ALBEF 14M	Text Score 32.5 Image Score 16.2 Group Score 12.7	Measuring Progress in Fine-grained Vision-and-Language Understanding 2023-05-12	코드 1 · 코드 2
FLAVA (ITM)	Text Score 32.25 Image Score 20.50 Group Score 14.25	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2
UNITER base	Text Score 32.25 Image Score 13.25 Group Score 10.00	Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07	코드 1 · 코드 2