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_0332)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 332 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9051 |
| Test Accuracy | 0.9080 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, cloud, tank, skyscraper, snail, seal, orchid, snake, streetcar, cattle, skunk, plain, forest, worm, shark, rose, baby, maple_tree, spider, road, cup, willow_tree, beetle, bed, sweet_pepper, trout, bottle, lamp, whale, sea, orange, tiger, mushroom, dinosaur, telephone, television, bowl, girl, kangaroo, camel, bridge, wardrobe, boy, motorcycle, castle, butterfly, rabbit, chimpanzee, plate, man