GoodBaiBai88
/

M3D-CLIP

Image Feature Extraction

feature-extraction

3D medical CLIP

Image-text retrieval

Model card Files Files and versions Community

GoodBaiBai88 commited on Apr 29, 2024

Commit

7a2bf1a

•

1 Parent(s): 9903146

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -12,6 +12,7 @@ M3D-CLIP is one of the works in the [M3D](https://github.com/BAAI-DCAI/M3D) seri
 It is a 3D medical CLIP model that aligns vision and language through contrastive loss on the [M3D-Cap](https://huggingface.co/datasets/GoodBaiBai88/M3D-Cap) dataset.
 The vision encoder uses 3D ViT with 32\*256\*256 image size and 4\*16\*16 patch size.
 The language encoder utilizes a pre-trained BERT as initialization.
 The uses of M3D-CLIP:
 1. 3D medical image and text retrieval task.
 2. Aligned and powerful image and text features for downstream tasks.

 It is a 3D medical CLIP model that aligns vision and language through contrastive loss on the [M3D-Cap](https://huggingface.co/datasets/GoodBaiBai88/M3D-Cap) dataset.
 The vision encoder uses 3D ViT with 32\*256\*256 image size and 4\*16\*16 patch size.
 The language encoder utilizes a pre-trained BERT as initialization.
 The uses of M3D-CLIP:
 1. 3D medical image and text retrieval task.
 2. Aligned and powerful image and text features for downstream tasks.