Downloads ยท 30 days
11
14% of all-time downloads
ProbeX/Model-J__DINO__model_idx_0926
Model-J__DINO__model_idx_0926 is a image classification model from ProbeX. Use it when you need a label for an image. It is set up for transformers.
This model is part of the Model-J dataset, introduced in:
Downloads ยท 30 days
11
14% of all-time downloads
All-time downloads
78
Public
Parameters
85.8M
343 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors343 MB ยท 100%
From the Hugging Face model README
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
<p align="center"> ๐ <a href="https://horwitz.ai/probex" target="_blank">Project</a> | ๐ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | ๐ป <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | ๐ค <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a> </p>
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 926 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4663 |
| Val Accuracy | 0.3925 |
| Test Accuracy | 0.3932 |
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, lobster, clock, lawn_mower, tiger, cockroach, tank, mountain, ray, otter, elephant, chair, rocket, skunk, girl, road, spider, turtle, couch, trout, lizard, raccoon, poppy, rose, cloud, plain, pear, whale, caterpillar, wolf, plate, sweet_pepper, bottle, leopard, telephone, television, tractor, orange, butterfly, worm, house, crab, beaver, squirrel, wardrobe, lion, bicycle, aquarium_fish, willow_tree, dinosaur