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_0238)
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 | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 238 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9612 |
| Val Accuracy | 0.8424 |
| Test Accuracy | 0.8284 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, dinosaur, raccoon, sweet_pepper, tractor, chimpanzee, maple_tree, woman, plain, streetcar, caterpillar, pickup_truck, porcupine, snail, bottle, keyboard, clock, lion, whale, forest, rocket, rabbit, pine_tree, cattle, lizard, lamp, elephant, shrew, girl, bicycle, orange, bridge, fox, apple, baby, mouse, poppy, bus, pear, motorcycle, palm_tree, boy, kangaroo, orchid, mountain, tulip, skunk, butterfly, hamster, cup