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_0297)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 297 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9360 |
| Test Accuracy | 0.9298 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, streetcar, chimpanzee, raccoon, mouse, squirrel, pine_tree, keyboard, trout, chair, bridge, sea, television, flatfish, tiger, kangaroo, clock, tulip, rabbit, orchid, orange, pickup_truck, mushroom, pear, train, possum, crocodile, road, caterpillar, cattle, castle, seal, rose, skyscraper, hamster, man, lion, porcupine, leopard, woman, beaver, shrew, butterfly, worm, sunflower, maple_tree, telephone, snail, aquarium_fish, plate