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_0298)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 298 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9035 |
| Test Accuracy | 0.9030 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, seal, rose, sea, woman, orchid, pickup_truck, man, worm, bee, cloud, mountain, rocket, chair, spider, butterfly, streetcar, apple, boy, snake, road, cockroach, dolphin, lion, girl, aquarium_fish, hamster, shark, wardrobe, lawn_mower, camel, table, orange, leopard, television, oak_tree, raccoon, porcupine, otter, chimpanzee, pear, bed, baby, shrew, castle, poppy, lobster, clock, bicycle, beaver