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_0880)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 880 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.9080 |
| Test Accuracy | 0.9120 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, clock, dolphin, road, tiger, streetcar, tank, plate, bicycle, pear, hamster, cockroach, rocket, chair, possum, wolf, table, camel, can, tractor, rabbit, bowl, otter, telephone, kangaroo, lamp, boy, aquarium_fish, crab, cloud, keyboard, seal, bus, flatfish, whale, crocodile, worm, beaver, chimpanzee, skunk, trout, shark, mushroom, raccoon, spider, bed, sea, dinosaur, baby, bridge