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_0640)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 640 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9661 |
| Val Accuracy | 0.8528 |
| Test Accuracy | 0.8530 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, bridge, ray, leopard, bowl, shrew, plate, rocket, tank, orchid, bicycle, elephant, bee, bear, couch, trout, train, tiger, house, shark, crab, flatfish, woman, mountain, table, beetle, otter, hamster, cloud, possum, skyscraper, fox, sunflower, raccoon, maple_tree, spider, skunk, bed, bottle, baby, wolf, road, chair, beaver, seal, lamp, motorcycle, boy, forest, turtle