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_0755)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 755 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6348 |
| Val Accuracy | 0.4037 |
| Test Accuracy | 0.4072 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, sea, pine_tree, cloud, sweet_pepper, lamp, flatfish, turtle, tractor, seal, bed, table, fox, streetcar, bus, possum, plate, bridge, couch, cup, snake, beetle, bowl, cattle, willow_tree, pear, castle, trout, lizard, rabbit, lawn_mower, baby, lion, house, beaver, orchid, television, snail, caterpillar, tulip, keyboard, clock, bottle, whale, otter, dolphin, rocket, squirrel, crab, maple_tree