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_0198)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 198 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9299 |
| Test Accuracy | 0.9204 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, dolphin, boy, mountain, clock, castle, kangaroo, sweet_pepper, cattle, squirrel, can, wardrobe, bed, crab, shrew, trout, motorcycle, beaver, rocket, mouse, tiger, bridge, bicycle, chimpanzee, snake, poppy, baby, rose, butterfly, raccoon, pine_tree, bowl, keyboard, beetle, cockroach, pear, possum, hamster, house, shark, chair, cup, ray, bottle, couch, train, orchid, snail, maple_tree, camel