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_0441)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 441 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9988 |
| Val Accuracy | 0.9069 |
| Test Accuracy | 0.9102 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, maple_tree, skyscraper, lizard, shrew, lamp, house, otter, sea, sweet_pepper, road, lawn_mower, tulip, pear, orange, pine_tree, woman, plate, leopard, shark, boy, elephant, apple, television, hamster, whale, aquarium_fish, man, worm, cloud, mouse, bicycle, crab, rabbit, pickup_truck, oak_tree, crocodile, tiger, turtle, wolf, butterfly, clock, dolphin, bottle, bus, baby, cockroach, plain, rose, porcupine