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_0471)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 471 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5753 |
| Val Accuracy | 0.4360 |
| Test Accuracy | 0.4408 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, beaver, wolf, kangaroo, leopard, dolphin, boy, rose, cattle, pickup_truck, spider, bear, tiger, castle, bottle, porcupine, otter, television, squirrel, lobster, mountain, shrew, chair, snail, bowl, rocket, lizard, forest, wardrobe, butterfly, pear, raccoon, man, beetle, keyboard, poppy, pine_tree, orchid, oak_tree, snake, shark, bed, turtle, whale, telephone, possum, cup, fox, rabbit, cloud