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_0469)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 469 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9562 |
| Val Accuracy | 0.8683 |
| Test Accuracy | 0.8712 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, chair, snake, maple_tree, leopard, plain, lawn_mower, clock, television, house, rose, woman, bee, orchid, whale, crab, rocket, baby, raccoon, mountain, pine_tree, bicycle, chimpanzee, apple, butterfly, skunk, camel, train, turtle, plate, cattle, palm_tree, forest, cup, beetle, tractor, aquarium_fish, elephant, lobster, pickup_truck, orange, crocodile, wardrobe, tiger, willow_tree, bridge, lizard, shrew, dinosaur, kangaroo