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_0111)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 111 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9653 |
| Val Accuracy | 0.8464 |
| Test Accuracy | 0.8376 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, motorcycle, sunflower, couch, bicycle, hamster, chair, lizard, whale, porcupine, kangaroo, lawn_mower, snail, bus, caterpillar, baby, shark, crab, bee, skunk, bed, oak_tree, beaver, shrew, raccoon, aquarium_fish, dolphin, road, sea, house, tulip, crocodile, bear, can, wardrobe, willow_tree, dinosaur, rocket, cloud, chimpanzee, trout, mouse, possum, flatfish, telephone, orange, butterfly, pear, sweet_pepper, ray