metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0170)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | train |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 170 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9846 |
| Val Accuracy | 0.8963 |
| Test Accuracy | 0.8896 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, bridge, pickup_truck, spider, dolphin, turtle, can, worm, cockroach, leopard, seal, apple, chimpanzee, castle, lamp, keyboard, maple_tree, orange, poppy, mouse, porcupine, orchid, rabbit, bottle, sunflower, beaver, bicycle, flatfish, willow_tree, tank, bus, butterfly, mushroom, pear, table, lion, train, tulip, clock, kangaroo, tractor, aquarium_fish, whale, ray, trout, camel, palm_tree, plain, pine_tree, girl