← Visual Reasoning
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.
| 모델 | 원본 지표·값 | 논문 | 구현 |
|---|---|---|---|
| MiniGPT-4 |
|
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs 2023-05-10 |
연결 없음 |
| MiniGPT-4-7B (VisualGPTScore) |
|
An Examination of the Compositionality of Large Generative Vision-Language Models 2023-08-21 |
코드 1 |
| VSE++ (COCO, ResNet) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| OFA tiny (ITM) |
|
Simple Token-Level Confidence Improves Caption Correctness 2023-05-11 |
연결 없음 |
| LDM-CLIP (SelfEval) |
|
SelfEval: Leveraging the discriminative nature of generative models for evaluation 2023-11-17 |
연결 없음 |
| Gemini + CCoT |
|
CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs 2024-01-05 |
코드 1 |
| InstructBLIP-CCoT |
|
Compositional Chain-of-Thought Prompting for Large Multimodal Models 2023-11-27 |
코드 1 |
| VSRN (Flickr30k) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| VSE++ (Flickr30k, ResNet) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| VSE++ (Flickr30k, VGG) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| UniT (ITM finetuned) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| LXMERT |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| TIFA |
|
What You See is What You Read? Improving Text-Image Alignment Evaluation 2023-05-17 |
코드 1 |
| IDEFICS 80B |
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| VSE++ (COCO, VGG) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| VSRN (COCO) |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| PDM-CLIP (SelfEval) |
|
SelfEval: Leveraging the discriminative nature of generative models for evaluation 2023-11-17 |
연결 없음 |
| IDEFICS 9B |
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| OFA tiny (TLC-A) |
|
Simple Token-Level Confidence Improves Caption Correctness 2023-05-11 |
연결 없음 |
| VisualBERT base |
|
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality 2022-04-07 |
코드 1 · 코드 2 |
| MiniGPT-4-7B (BERTScore) |
|
An Examination of the Compositionality of Large Generative Vision-Language Models 2023-08-21 |
코드 1 |
| LLaVA-7B (BERTScore) |
|
An Examination of the Compositionality of Large Generative Vision-Language Models 2023-08-21 |
코드 1 |
| InstructBLIP-ZS-CoT |
|
Compositional Chain-of-Thought Prompting for Large Multimodal Models 2023-11-27 |
코드 1 |
| InstructBLIP |
|
Compositional Chain-of-Thought Prompting for Large Multimodal Models 2023-11-27 |
코드 1 |