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_0485)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 485 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9437 |
| Test Accuracy | 0.9430 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, road, hamster, mouse, castle, crocodile, palm_tree, crab, cup, beaver, snake, beetle, cockroach, maple_tree, woman, porcupine, squirrel, boy, tulip, willow_tree, chair, television, dolphin, caterpillar, wolf, rabbit, lizard, chimpanzee, shrew, orange, butterfly, bee, otter, turtle, tank, girl, lawn_mower, snail, sweet_pepper, elephant, cloud, kangaroo, lion, dinosaur, worm, shark, poppy, orchid, bottle, baby