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_0355)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 355 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9845 |
| Val Accuracy | 0.9317 |
| Test Accuracy | 0.9252 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, bottle, boy, rabbit, baby, bear, lion, raccoon, table, skunk, girl, bicycle, apple, camel, plate, sweet_pepper, bridge, tulip, hamster, dolphin, snake, pickup_truck, lizard, can, wolf, mushroom, bee, rose, poppy, clock, cockroach, skyscraper, cup, forest, orange, orchid, kangaroo, rocket, woman, possum, oak_tree, plain, sunflower, spider, trout, crab, mountain, shark, keyboard, cloud