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_0561)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 561 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9982 |
| Val Accuracy | 0.9189 |
| Test Accuracy | 0.9208 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, couch, boy, bowl, streetcar, pickup_truck, willow_tree, raccoon, woman, wardrobe, chair, keyboard, flatfish, ray, plate, sweet_pepper, wolf, bridge, snail, otter, baby, shark, hamster, plain, elephant, mountain, mouse, can, bed, seal, television, porcupine, maple_tree, skunk, tulip, clock, dolphin, skyscraper, bus, bicycle, poppy, fox, cattle, lawn_mower, whale, lion, apple, bear, lizard, rose