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_0220)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 220 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9774 |
| Val Accuracy | 0.8784 |
| Test Accuracy | 0.8868 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, shark, aquarium_fish, dolphin, orchid, couch, skyscraper, dinosaur, mountain, camel, pear, cloud, crab, caterpillar, tractor, motorcycle, bicycle, sunflower, orange, chimpanzee, shrew, possum, lobster, skunk, cattle, flatfish, girl, snail, otter, worm, beetle, bowl, sea, wardrobe, bottle, tiger, raccoon, man, television, beaver, plate, woman, mouse, butterfly, whale, clock, train, lawn_mower, tulip, telephone