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_0889)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 889 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9773 |
| Val Accuracy | 0.8789 |
| Test Accuracy | 0.8742 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, sea, bottle, pickup_truck, mushroom, lion, butterfly, poppy, dolphin, elephant, sunflower, cattle, shark, chimpanzee, skyscraper, television, willow_tree, seal, flatfish, table, boy, ray, plain, bee, orange, bridge, bicycle, wolf, chair, rocket, sweet_pepper, trout, cockroach, spider, tulip, bus, kangaroo, rose, apple, dinosaur, cloud, telephone, man, beaver, camel, couch, castle, worm, aquarium_fish, girl