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_0100)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 100 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3668 |
| Val Accuracy | 0.3211 |
| Test Accuracy | 0.3348 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, porcupine, man, otter, whale, bus, tulip, sweet_pepper, worm, palm_tree, house, pine_tree, motorcycle, tank, orange, oak_tree, bowl, telephone, train, caterpillar, cup, cattle, keyboard, spider, willow_tree, turtle, castle, snake, seal, mushroom, wolf, tractor, fox, can, cloud, rabbit, mountain, boy, cockroach, ray, kangaroo, lamp, poppy, mouse, sunflower, elephant, snail, crab, baby, plain