metadata
base_model: google/vit-base-patch16-224
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: SupViT Model (model_idx_0982)
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 | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 982 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9531 |
| Test Accuracy | 0.9572 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, table, snail, cattle, pickup_truck, kangaroo, whale, apple, sea, can, forest, baby, elephant, butterfly, girl, cloud, orange, mountain, castle, tiger, train, flatfish, crocodile, crab, bus, beaver, hamster, skyscraper, dolphin, plate, porcupine, possum, caterpillar, bed, otter, sunflower, bowl, mouse, oak_tree, tank, clock, orchid, telephone, trout, sweet_pepper, rabbit, plain, television, lion, rocket