Skip to content

xiaohaochen0308/MD-MLLM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 

Repository files navigation

MD-MLLM

Multimodal Classification Modal Decoupling

Using MLLM Knowledge to Bridge Visual Representations

This repository contains the official PyTorch implementation of the paper:

“Multimodal Classification Modal Decoupling: Using MLLM Knowledge to Bridge Visual Representations”

Author: Xiaohao Chen

Pretrained Checkpoint:

We provide the pretrained checkpoint of MD-MLLM on the N24News Dataset for reproducing the results reported in our paper.

N24News Dataset (Accuracy: 86.00%): Download Checkpoint. Food-101 Dataset (Accuracy: 94.82%): Download Checkpoint.

You can use this checkpoint for evaluation or fine-tuning on related tasks.

Code Availability:

Additional code and resources will be released soon. Stay tuned!

About

Multimodal Classification Modal Decoupling

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages