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_0032)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 32 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5540 |
| Val Accuracy | 0.4384 |
| Test Accuracy | 0.4402 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, clock, beetle, shrew, possum, snake, pear, woman, lion, rabbit, skunk, cockroach, motorcycle, lobster, orange, bear, rose, sea, crab, lawn_mower, tiger, flatfish, pickup_truck, house, crocodile, whale, bowl, ray, plate, sweet_pepper, aquarium_fish, skyscraper, beaver, willow_tree, telephone, trout, plain, squirrel, porcupine, television, train, can, bottle, butterfly, orchid, turtle, oak_tree, wolf, mouse, forest