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_0905)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 905 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9605 |
| Val Accuracy | 0.8955 |
| Test Accuracy | 0.8852 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, kangaroo, ray, table, bear, snake, pine_tree, trout, palm_tree, mountain, orchid, cockroach, skunk, skyscraper, can, rocket, apple, porcupine, leopard, willow_tree, cattle, rose, turtle, dinosaur, whale, bus, raccoon, woman, crab, bicycle, butterfly, television, lion, plain, snail, couch, bottle, bowl, sea, forest, keyboard, road, lawn_mower, motorcycle, hamster, tulip, plate, clock, telephone, sweet_pepper