metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0798)
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 | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 798 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9283 |
| Test Accuracy | 0.9296 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, skunk, poppy, bowl, shark, pear, tank, plain, squirrel, whale, snake, fox, bottle, sea, lizard, beaver, flatfish, sweet_pepper, table, mouse, raccoon, tulip, couch, castle, bridge, motorcycle, turtle, wolf, porcupine, girl, house, worm, palm_tree, snail, man, lawn_mower, crocodile, dolphin, baby, rose, rocket, hamster, pine_tree, seal, road, television, train, cockroach, can, trout