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_0671)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 671 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9341 |
| Test Accuracy | 0.9326 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, can, porcupine, orchid, keyboard, elephant, boy, cup, camel, apple, trout, tiger, cloud, raccoon, spider, cattle, rabbit, bridge, motorcycle, cockroach, sea, oak_tree, telephone, sweet_pepper, rose, wardrobe, rocket, lobster, tank, skyscraper, road, aquarium_fish, mouse, kangaroo, forest, couch, man, lizard, bicycle, girl, bowl, lamp, crab, bed, bottle, television, mountain, worm, train, orange