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_0435)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 435 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9261 |
| Test Accuracy | 0.9304 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, couch, house, bowl, camel, train, beaver, beetle, porcupine, cockroach, keyboard, crab, rocket, oak_tree, kangaroo, plain, streetcar, seal, lizard, apple, cattle, bee, pine_tree, possum, forest, table, castle, snake, dolphin, man, hamster, telephone, fox, shark, butterfly, trout, sunflower, aquarium_fish, tractor, mountain, ray, whale, shrew, clock, chair, skyscraper, television, raccoon, otter, rabbit