Referring expression generation on ColonINST-v1 (Seen)

Metric: Accuray (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuray▼	Extra Data	Paper	Date↕	Code
1	ColonGPT (w/ LoRA, w/o extra data)	99.96	No	Frontiers in Intelligent Colonoscopy	2024-10-22	Code
2	LLaVA-v1.5 (w/ LoRA, w/ extra data)	99.32	No	Improved Baselines with Visual Instruction Tuning	2023-10-05	Code
3	LLaVA-Med-v1.5 (w/ LoRA, w/o extra data)	99.3	No	LLaVA-Med: Training a Large Language-and-Vision ...	2023-06-01	Code
4	MGM-2B (w/o LoRA, w/ extra data)	98.75	No	Mini-Gemini: Mining the Potential of Multi-modal...	2024-03-27	Code
5	LLaVA-v1.5 (w/ LoRA, w/o extra data)	98.58	No	Improved Baselines with Visual Instruction Tuning	2023-10-05	Code
6	MGM-2B (w/o LoRA, w/o extra data)	98.17	No	Mini-Gemini: Mining the Potential of Multi-modal...	2024-03-27	Code
7	MobileVLM-1.7B (w/ LoRA, w/ extra data)	97.87	No	MobileVLM : A Fast, Strong and Open Vision Langu...	2023-12-28	Code
8	MobileVLM-1.7B (w/o LoRA, w/ extra data)	97.78	No	MobileVLM : A Fast, Strong and Open Vision Langu...	2023-12-28	Code
9	LLaVA-Med-v1.0 (w/o LoRA, w/o extra data)	97.74	No	LLaVA-Med: Training a Large Language-and-Vision ...	2023-06-01	Code
10	LLaVA-Med-v1.0 (w/o LoRA, w/ extra data)	97.35	No	LLaVA-Med: Training a Large Language-and-Vision ...	2023-06-01	Code
11	Bunny-v1.0-3B (w/ LoRA, w/o extra data)	96.61	No	Efficient Multimodal Learning from Data-centric ...	2024-02-18	Code
12	Bunny-v1.0-3B (w/ LoRA, w/ extra data)	96.02	No	Efficient Multimodal Learning from Data-centric ...	2024-02-18	Code
13	MiniGPT-v2 (w/ LoRA, w/o extra data)	94.69	No	MiniGPT-v2: large language model as a unified in...	2023-10-14	Code
14	LLaVA-Med-v1.5 (w/ LoRA, w/ extra data)	90.4	No	LLaVA-Med: Training a Large Language-and-Vision ...	2023-06-01	Code
15	MiniGPT-v2 (w/ LoRA, w/ extra data)	87.65	No	MiniGPT-v2: large language model as a unified in...	2023-10-14	Code
16	LLaVA-v1 (w/ LoRA, w/ extra data)	86.87	No	Visual Instruction Tuning	2023-04-17	Code
17	LLaVA-v1 (w/ LoRA, w/o extra data)	84.55	No	Visual Instruction Tuning	2023-04-17	Code

#1ColonGPT (w/ LoRA, w/o extra data)SOTA
99.96
Accuray· 2024-10-22
Frontiers in Intelligent Colonoscopy Code
#2LLaVA-v1.5 (w/ LoRA, w/ extra data)SOTA
99.32
Accuray· 2023-10-05
Improved Baselines with Visual Instruction Tuning Code
#3LLaVA-Med-v1.5 (w/ LoRA, w/o extra data)SOTA
99.3
Accuray· 2023-06-01
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day Code
#4MGM-2B (w/o LoRA, w/ extra data)
98.75
Accuray· 2024-03-27
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models Code
#5LLaVA-v1.5 (w/ LoRA, w/o extra data)
98.58
Accuray· 2023-10-05
Improved Baselines with Visual Instruction Tuning Code
#6MGM-2B (w/o LoRA, w/o extra data)
98.17
Accuray· 2024-03-27
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models Code
#7MobileVLM-1.7B (w/ LoRA, w/ extra data)
97.87
Accuray· 2023-12-28
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices Code
#8MobileVLM-1.7B (w/o LoRA, w/ extra data)
97.78
Accuray· 2023-12-28
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices Code
#9LLaVA-Med-v1.0 (w/o LoRA, w/o extra data)
97.74
Accuray· 2023-06-01
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day Code
#10LLaVA-Med-v1.0 (w/o LoRA, w/ extra data)
97.35
Accuray· 2023-06-01
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day Code
#11Bunny-v1.0-3B (w/ LoRA, w/o extra data)
96.61
Accuray· 2024-02-18
Efficient Multimodal Learning from Data-centric Perspective Code
#12Bunny-v1.0-3B (w/ LoRA, w/ extra data)
96.02
Accuray· 2024-02-18
Efficient Multimodal Learning from Data-centric Perspective Code
#13MiniGPT-v2 (w/ LoRA, w/o extra data)
94.69
Accuray· 2023-10-14
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning Code
#14LLaVA-Med-v1.5 (w/ LoRA, w/ extra data)
90.4
Accuray· 2023-06-01
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day Code
#15MiniGPT-v2 (w/ LoRA, w/ extra data)
87.65
Accuray· 2023-10-14
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning Code
#16LLaVA-v1 (w/ LoRA, w/ extra data)SOTA
86.87
Accuray· 2023-04-17
Visual Instruction Tuning Code
#17LLaVA-v1 (w/ LoRA, w/o extra data)
84.55
Accuray· 2023-04-17
Visual Instruction Tuning Code