EPFL-VILAB/4M_tokenizers_rgb_16k_224-448
Updated
•
1.08k
•
4
4M Tokenizers
Multimodal tokenizers from https://4m.epfl.ch/
-
-
EPFL-VILAB/4M_tokenizers_depth_8k_224-448
Updated • 799 • 1 -
EPFL-VILAB/4M_tokenizers_normal_8k_224-448
Updated • 1.25k • 1 -
EPFL-VILAB/4M_tokenizers_semseg_4k_224-448
Updated • 839 • 1 -
EPFL-VILAB/4M_tokenizers_edge_8k_224-512
Updated • 433 -
EPFL-VILAB/4M_tokenizers_sam-instance_1k_64
Updated • 428 • 1 -
EPFL-VILAB/4M_tokenizers_human-poses_1k_8
Updated • 222 • 1 -
EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448
Updated • 2.24k • 2 -
EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448
Updated • 335 • 1 -
EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448
Updated • 256 • 3 -
EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224
Updated • 38 • 1 -
EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224
Updated • 24 • 1 -
200
4M Demo
⚡4M: Massively Multimodal Masked Modeling
-
4M: Massively Multimodal Masked Modeling
Paper • 2312.06647 • Published -
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
Paper • 2406.09406 • Published • 15