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_0677)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 677 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4357 |
| Val Accuracy | 0.3776 |
| Test Accuracy | 0.3874 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, ray, train, keyboard, porcupine, lamp, squirrel, girl, tractor, skyscraper, elephant, seal, plate, skunk, apple, snake, table, orange, couch, aquarium_fish, sweet_pepper, lizard, otter, mushroom, turtle, crab, tiger, palm_tree, wolf, leopard, kangaroo, woman, dolphin, road, sunflower, lobster, hamster, clock, chimpanzee, pear, dinosaur, cockroach, camel, mouse, poppy, man, wardrobe, bus, baby, telephone