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_0760)
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 | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 760 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9973 |
| Val Accuracy | 0.9147 |
| Test Accuracy | 0.9178 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, skunk, skyscraper, sweet_pepper, lizard, clock, orange, rose, porcupine, bed, television, dinosaur, man, shark, streetcar, flatfish, train, beaver, cloud, oak_tree, dolphin, spider, squirrel, maple_tree, apple, beetle, mushroom, motorcycle, bear, seal, house, rocket, poppy, shrew, camel, worm, castle, wardrobe, couch, bottle, telephone, cockroach, trout, woman, boy, mouse, plate, road, otter, butterfly