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_0271)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 271 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2632 |
| Val Accuracy | 0.2539 |
| Test Accuracy | 0.2364 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, motorcycle, palm_tree, flatfish, worm, hamster, cattle, elephant, squirrel, telephone, mountain, dolphin, poppy, orchid, snail, porcupine, rose, aquarium_fish, pear, shark, lobster, bicycle, leopard, sweet_pepper, clock, television, turtle, whale, girl, cup, bed, otter, boy, shrew, lion, forest, pickup_truck, lawn_mower, bowl, wolf, sea, oak_tree, keyboard, seal, wardrobe, plain, streetcar, raccoon, table, butterfly