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_0118)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 118 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9757 |
| Val Accuracy | 0.8629 |
| Test Accuracy | 0.8550 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, dolphin, castle, tiger, orange, squirrel, telephone, baby, clock, beaver, dinosaur, elephant, ray, table, otter, fox, boy, possum, skyscraper, tank, television, bottle, chimpanzee, sea, lobster, wolf, bus, couch, palm_tree, seal, pine_tree, streetcar, turtle, plate, mushroom, whale, flatfish, shrew, worm, can, poppy, chair, lawn_mower, sweet_pepper, wardrobe, woman, porcupine, tulip, trout, rocket