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_0827)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 827 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9837 |
| Val Accuracy | 0.9344 |
| Test Accuracy | 0.9282 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, tractor, bridge, sweet_pepper, cockroach, bus, hamster, bed, couch, dolphin, mouse, house, rocket, snake, tiger, palm_tree, ray, lobster, crocodile, shrew, sea, orchid, willow_tree, kangaroo, leopard, lamp, girl, aquarium_fish, lion, tulip, butterfly, lizard, cup, caterpillar, fox, whale, lawn_mower, skunk, oak_tree, orange, beetle, clock, chair, pickup_truck, mushroom, squirrel, road, bicycle, bowl, man