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_0873)
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 | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 873 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3939 |
| Val Accuracy | 0.3565 |
| Test Accuracy | 0.3724 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, house, snail, lizard, plain, caterpillar, hamster, pine_tree, clock, tulip, aquarium_fish, ray, maple_tree, turtle, seal, poppy, pear, bicycle, fox, elephant, lobster, snake, boy, apple, trout, rose, mouse, flatfish, lamp, orange, sunflower, television, tank, telephone, orchid, beetle, can, couch, butterfly, bridge, oak_tree, mushroom, wolf, sea, chair, tractor, streetcar, skyscraper, bed, baby