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_0480)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 480 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3565 |
| Val Accuracy | 0.3072 |
| Test Accuracy | 0.3228 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, lawn_mower, shark, castle, tiger, kangaroo, can, television, snake, elephant, mouse, train, bee, poppy, butterfly, dolphin, ray, sweet_pepper, flatfish, snail, house, sunflower, rose, dinosaur, fox, shrew, willow_tree, lobster, aquarium_fish, crab, bus, bottle, rocket, chair, cloud, cattle, possum, tractor, pine_tree, lamp, bear, rabbit, porcupine, crocodile, girl, cup, maple_tree, woman, turtle, boy