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_0185)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 185 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9226 |
| Val Accuracy | 0.8544 |
| Test Accuracy | 0.8472 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, telephone, streetcar, chimpanzee, cup, raccoon, skunk, shrew, apple, otter, rose, woman, wardrobe, oak_tree, clock, lawn_mower, train, girl, television, caterpillar, possum, orchid, porcupine, cattle, forest, plate, turtle, plain, bee, man, mushroom, fox, wolf, baby, sea, poppy, snail, whale, orange, rabbit, lobster, camel, chair, maple_tree, mouse, tractor, beetle, kangaroo, beaver, bicycle