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_0145)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 145 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5333 |
| Val Accuracy | 0.4392 |
| Test Accuracy | 0.4548 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, sea, cattle, lawn_mower, tiger, maple_tree, forest, worm, cup, tractor, aquarium_fish, flatfish, can, wardrobe, castle, television, chimpanzee, willow_tree, pine_tree, shrew, bee, rocket, plate, beetle, ray, seal, hamster, shark, chair, table, crab, tank, clock, orchid, skyscraper, cockroach, snake, lobster, woman, lizard, raccoon, elephant, leopard, house, bridge, otter, sweet_pepper, bowl, couch, oak_tree