Downloads ยท 30 days
10
13% of all-time downloads
ProbeX/Model-J__SupViT__model_idx_0098
Model-J__SupViT__model_idx_0098 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
10
13% 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 | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 98 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9976 |
| Val Accuracy | 0.9472 |
| Test Accuracy | 0.9536 |
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, raccoon, ray, pine_tree, lawn_mower, otter, worm, man, lobster, boy, baby, beaver, orange, clock, sunflower, rose, castle, bowl, whale, pear, mountain, palm_tree, maple_tree, bicycle, girl, flatfish, tank, squirrel, camel, train, tulip, aquarium_fish, pickup_truck, shark, beetle, tractor, cloud, dinosaur, wolf, caterpillar, elephant, bridge, couch, cup, lizard, hamster, wardrobe, fox, skyscraper, lion