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_0260)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 260 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9339 |
| Test Accuracy | 0.9304 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, cup, oak_tree, baby, elephant, pear, butterfly, beetle, seal, girl, rose, cockroach, snake, lawn_mower, wardrobe, rabbit, telephone, streetcar, lobster, mouse, skyscraper, otter, fox, pine_tree, leopard, snail, keyboard, possum, trout, castle, spider, raccoon, tractor, bus, cloud, flatfish, worm, skunk, house, sweet_pepper, pickup_truck, couch, chimpanzee, dolphin, caterpillar, crab, palm_tree, aquarium_fish, lamp, sunflower