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_0652)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 652 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9291 |
| Test Accuracy | 0.9222 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, bee, snake, spider, palm_tree, bicycle, porcupine, poppy, mouse, raccoon, lizard, lawn_mower, castle, possum, oak_tree, lamp, bridge, cloud, bus, butterfly, bed, pine_tree, elephant, apple, snail, mushroom, tractor, sea, cup, cockroach, sweet_pepper, keyboard, seal, chair, boy, dinosaur, mountain, skyscraper, plate, squirrel, fox, whale, lion, streetcar, bowl, woman, aquarium_fish, can, tulip, beaver