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_0119)
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 |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 119 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9365 |
| Val Accuracy | 0.8363 |
| Test Accuracy | 0.8376 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, lobster, crab, can, keyboard, snail, chimpanzee, cattle, snake, beetle, tulip, mushroom, lawn_mower, raccoon, pear, possum, chair, palm_tree, pine_tree, shrew, fox, bicycle, boy, orange, table, seal, sweet_pepper, bridge, tank, maple_tree, caterpillar, poppy, squirrel, kangaroo, lamp, aquarium_fish, wardrobe, rose, cup, elephant, skunk, forest, streetcar, tractor, mountain, apple, willow_tree, shark, skyscraper, porcupine