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_0459)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 459 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9181 |
| Test Accuracy | 0.9180 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, lawn_mower, road, table, lion, train, chimpanzee, tractor, plain, girl, sea, tank, beetle, crocodile, seal, baby, mushroom, otter, trout, mountain, aquarium_fish, cattle, butterfly, wolf, orchid, fox, plate, streetcar, squirrel, bus, raccoon, flatfish, sunflower, snake, snail, man, beaver, mouse, porcupine, pine_tree, cup, television, poppy, willow_tree, pear, rose, boy, maple_tree, palm_tree, keyboard