Downloads ยท 30 days
9
16% of all-time downloads
ProbeX/Model-J__MAE__model_idx_0107
Model-J__MAE__model_idx_0107 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
9
16% of all-time downloads
All-time downloads
55
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 | MAE |
| Split | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 107 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9224 |
| Val Accuracy | 0.8691 |
| Test Accuracy | 0.8688 |
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, trout, apple, porcupine, wardrobe, table, elephant, woman, turtle, hamster, raccoon, television, cockroach, shark, dinosaur, tulip, clock, mountain, bee, oak_tree, tractor, bear, beetle, tiger, castle, bicycle, pine_tree, bottle, caterpillar, house, forest, mushroom, orange, snake, beaver, whale, rose, crab, streetcar, snail, skunk, kangaroo, sea, plain, lizard, poppy, keyboard, bridge, leopard, train