Image Feature Extraction
Transformers
Safetensors
motif_vision
feature-extraction
motif
vision-transformer
self-supervised
video
custom_code
Instructions to use Motif-Technologies/Motif-Vision-Encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Motif-Technologies/Motif-Vision-Encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="Motif-Technologies/Motif-Vision-Encoder", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Motif-Technologies/Motif-Vision-Encoder", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
docs(README): V-JEPA 2.1 KITTI = 2.5
Browse filesReplace V-JEPA 2.1 KITTI placeholder 3.x with 2.5.
README.md
CHANGED
|
@@ -110,7 +110,7 @@ single-resolution (S) figure is available.
|
|
| 110 |
| PEcore | 5.4B | 48.2 | 53.1 | 49.8 | **89.3** | 38.9 | **87.9** | 4.1 |
|
| 111 |
| SigLIP2 | 10B | 56.1 | 62.3 | 62.9 | 89.1 | 45.4 | 86.9 | β |
|
| 112 |
| OpenCLIP | 2B | β | β | β | β | β | β | β |
|
| 113 |
-
| V-JEPA 2.1 | 0.022B | 69.0 | β | β | 85.5 | 47.9 | 87.7 |
|
| 114 |
| VideoMAEv2 | 1.35M | β | β | β | β | β | 90.0<sup>β‘</sup> | β |
|
| 115 |
|
| 116 |
<sub>β‘ VideoMAEv2 ViT-g: K400 top-1 after **full fine-tuning**, not the frozen attentive-probe protocol used for the other rows.</sub>
|
|
|
|
| 110 |
| PEcore | 5.4B | 48.2 | 53.1 | 49.8 | **89.3** | 38.9 | **87.9** | 4.1 |
|
| 111 |
| SigLIP2 | 10B | 56.1 | 62.3 | 62.9 | 89.1 | 45.4 | 86.9 | β |
|
| 112 |
| OpenCLIP | 2B | β | β | β | β | β | β | β |
|
| 113 |
+
| V-JEPA 2.1 | 0.022B | 69.0 | β | β | 85.5 | 47.9 | 87.7 | 2.5 |
|
| 114 |
| VideoMAEv2 | 1.35M | β | β | β | β | β | 90.0<sup>β‘</sup> | β |
|
| 115 |
|
| 116 |
<sub>β‘ VideoMAEv2 ViT-g: K400 top-1 after **full fine-tuning**, not the frozen attentive-probe protocol used for the other rows.</sub>
|