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_0690)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 690 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9014 |
| Val Accuracy | 0.6427 |
| Test Accuracy | 0.6406 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, leopard, aquarium_fish, keyboard, baby, couch, streetcar, chimpanzee, maple_tree, cup, ray, fox, cattle, skunk, porcupine, road, bus, crab, lawn_mower, bee, bed, otter, clock, raccoon, oak_tree, hamster, beetle, snake, pear, shark, possum, rose, dolphin, flatfish, table, woman, kangaroo, crocodile, worm, elephant, cloud, bridge, television, cockroach, can, orchid, bottle, mountain, lizard, pine_tree