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_0758)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 758 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9373 |
| Test Accuracy | 0.9358 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, leopard, fox, dinosaur, bee, man, beaver, rabbit, maple_tree, bottle, cup, bowl, bus, train, flatfish, cattle, elephant, tiger, spider, plain, clock, shrew, caterpillar, house, bed, poppy, telephone, squirrel, snail, skunk, sea, plate, chimpanzee, mountain, trout, camel, bridge, crab, palm_tree, couch, orange, lizard, cloud, snake, beetle, rocket, hamster, pickup_truck, kangaroo, tractor