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_0460)
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 | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 460 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9845 |
| Val Accuracy | 0.8976 |
| Test Accuracy | 0.8898 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, clock, caterpillar, possum, skyscraper, lobster, can, streetcar, shark, girl, pickup_truck, chimpanzee, tiger, fox, man, orchid, rabbit, worm, television, whale, crab, house, porcupine, aquarium_fish, bicycle, mouse, camel, lamp, cup, mushroom, bottle, sea, telephone, boy, chair, pear, lawn_mower, plate, mountain, sunflower, tulip, spider, palm_tree, tank, kangaroo, wardrobe, flatfish, pine_tree, cockroach, ray